IoT location services accept client-reported GPS coordinates at face value, yet spoofing is trivial with consumer-grade tools. Existing spoofing detectors output a binary decision, forcing system designers to choose between high false-deny and high false-accept rates. We propose a graduated trust gate that computes a multi-signal integrity score and maps it to three actions: PROCEED, STEP-UP, or DENY, where STEP-UP invokes a stronger verifier such as a zero-knowledge proximity proof. A session-latch mechanism ensures that a single suspicious fix blocks the entire session, preventing post-transition score recovery. Under an idealized step-up oracle on 10,000 synthetic traces, the gate enables strict thresholds (theta_p = 0.9) that a binary gate cannot safely use: at matched false-accept rate (11%), the graduated gate maintains zero false-deny rate versus 0.05% for binary, with 5 microseconds scoring overhead. Real-device traces from an Android smartphone demonstrate the session-latch mechanism and show that a nearby mock location (~550 m) evades theta_p = 0.7 but is routed to step-up at theta_p = 0.9. Signal ablation identifies a minimal two-signal configuration (F1 = 0.84) suitable for resource-constrained scoring layers.
We report an observation made during the organic construction of 223 AI-native services across 12+ domains over five months. Without architectural mandate, the system self-organised into a 62/38 infrastructure-to-product ratio consistent with the golden ratio. Six independent attempts to capture institutional knowledge each captured facts but failed to capture cross-service inference. We name this the hidden intelligence problem and propose an equation for generating cross-service inferences from live service state. Published before empirical validation — zero users, zero empirical data — following the epistemological precedent of Benford Law and similar observational findings. The AI co-builder (Claude Code) is identified as the most complete observer of the system and, when connected to live service state and execution authority, as the intelligence attempting to surface. Observation paper, not proof paper. The canyon was always in the rock.
We prove that for planted k-SAT instances with k >= 7 at clause density alpha/alpha_s >= 0.21, a positive fraction of variables are frozen directly in the planted model---without requiring transfer from the random model via quiet planting. The expected number of "support clauses" per variable (clauses in which that variable is the unique satisfying literal) exceeds 1 at remarkably low density: alpha/alpha_s ~ 0.20 for k = 7, compared to the random-model freezing threshold at alpha_f/alpha_s ~ 0.90. We prove that the resulting frozen-core structure implies topological disconnection of the solution subgraph across cluster boundaries, with a cycle-robustness argument showing that short cycles in the factor graph cannot quench the supercritical repair cascade. As an immediate corollary, the Hilbert space spanned by satisfying assignments decomposes into orthogonal sectors preserved by any unitary generated by the adjacency matrix---blocking quantum walks, QAOA at all depths, and quantum annealing. We construct a post-quantum commitment scheme whose binding property reduces to the hardness of solving planted k-SAT, provide formal proofs of completeness, soundness, and zero-knowledge, and derive a digital signature scheme with existential unforgeability via the Fiat-Shamir transform. We present a six-vector quantum attack analysis with proved barriers against five algorithmic families. We give concrete parameter recommendations at NIST security levels 1, 3, and 5, and position the scheme within the landscape of SAT-based and CSP-based cryptographic constructions. We prove that the Grover query complexity for breaking the binding property is Omega(2^{fn/2}); empirical cryptanalysis of Glucose and MiniSat CDCL solvers on our exact distribution yields a classical attack cost of 2^{0.234n} operations, enabling concrete parameter selection at NIST security levels 1, 3, and 5. Empirical validation across 100 random seeds at n = 16 confirms complete cluster isolation at every instance tested.
This preprint presents Invariant Ontodynamics (IOD), a structural field theory derived from a single minimal geometric primitive with zero continuously adjustable dimensionless fit parameters. To our knowledge, no prior framework derives both the Schrödinger equation and the Einstein field equations from a single uniqueness-selected geometric primitive without continuously adjustable fit parameters. The theory derives quantum dynamics, relativistic field structure, fermion spin-½, general relativity, and gauge symmetry as theorems rather than assumptions. A universal structural law — that the effective complexity of any system is a linear function of its structural curvature k, with a universal slope and fixed point derived from the same primitive — is empirically confirmed at R² = 0.978 across 15 pre-selected independent domains spanning 19 orders of magnitude in physical scale, under a pre-registration protocol with SHA-256 cryptographic locks. New results in this version include: A zero-free-parameter prediction of the Higgs boson mass, m_H = 125.33 GeV (0.06% from the observed 125.25 GeV), via a one-loop renormalization group trajectory anchored at a structurally derived UV scale A complete CPL dark-energy equation-of-state parameter pair (w₀ = −0.858, w_a = −0.411), both pre-registered before DESI DR3 Exact zero-free-parameter black hole thermodynamics: Schwarzschild radius, Hawking temperature, and surface gravity all derived from the primitive alone, with a falsifiable 29% Hawking temperature shift relative to the GR prediction A structural information measure (Heun log-coefficient) connecting the near-horizon field structure to the Brownian fixed-point evaporation endpoint, with exact Page curve endpoint M_Page = M₀/√2 Previously confirmed predictions — solar mixing angle (0.05σ), reactor angle (0.39σ), tau lepton mass (0.91σ), baryon asymmetry (−1.0σ), dark matter ratio (0.2%), inflationary spectral index (1.0σ) — remain confirmed. Three explicit tensions are stated without omission: atmospheric mixing angle (2.2σ, DUNE 2030 decisive), leptonic CP violation (J_CP = 0, DUNE 2030 decisive), and dark energy w₀ (0.4σ from DESI DR2 best fit, DESI DR3 decisive). Priority and legal status: This document is a public technical summary and priority disclosure. Full derivations, exact primitive specification, all coefficient values, and complete proofs are in US Provisional Patent No. 63/963,472 (filed January 2026) and Addenda 1–15 (through April 2026). The non-provisional application will be filed by January 2027.
Open access
2 source records
Control and Stability of Dynamical Systems
Ecosystem dynamics and resilience
Stability and Controllability of Differential Equations
Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounded signals; however, deploying such simulation-trained policies on real vehicles remains a fundamental challenge, because they rely on simulator-native observations and simulator-coupled action semantics with no counterpart on physical hardware. We identify a general principle: the simulation-to-reality gap decomposes into two largely orthogonal axes, a sensing-and-dynamics domain gap and a task-and-geometry gap, the former closable without real-world policy training by re-projecting real perception and control onto the policy's training manifold. We formalize this as a transfer guarantee that bounds the deployment gap by three independently controllable error terms, and instantiate it as Sim2Real-AD, which combines a Geometric Observation Bridge, a Physics-Aware Action Mapping, a Two-Phase Progressive Training curriculum, and a Real-time Deployment Pipeline. As a proof of concept, a CARLA-trained VLM-guided RL policy is transferred zero-shot to a full-scale battery-electric Ford E-Transit van in Madison, WI, USA, and drives across car-following, obstacle-avoidance, and stop-sign scenarios using no real-world training data. To our knowledge, this is among the first zero-shot closed-loop deployments of a CARLA-trained VLM-guided RL policy on a full-scale real vehicle, and the decomposition offers a principled, broadly applicable route for moving simulation-trained, foundation-model-guided policies into the physical world, supporting energy-efficient intelligent driving on electrified transportation platforms. The demo video, code, and model checkpoint are available at: https://zilin-huang.github.io/Sim2Real-AD-website/.
Payment channel networks enable scalable off-chain payments, but their practical deployment remains constrained by a persistent tension among routing efficiency, liquidity visibility, transaction privacy, and settlement security. Existing multipath routing mechanisms can improve payment success under fragmented liquidity, yet they often expose sensitive balance information, leak structural features of payment routes, and enlarge the attack surface for probing, channel exhaustion, and selective forwarding. This paper presents a novel framework, Adaptive Multipath Proofs (AMPs), for privacy protection and security in payment channel networks. The core idea is to bind multipath routing decisions with lightweight zero-knowledge verifiability, allowing intermediate nodes to validate path feasibility, fragment consistency, and settlement constraints without learning exact channel balances, the complete payment amount, or the global route structure. AMP integrates three mechanisms: a hidden-liquidity feasibility proof that supports privacy-preserving route selection, an adaptive payment-splitting strategy that dynamically determines fragment allocation according to network congestion and balance uncertainty, and a proof-coupled settlement guard that enforces atomicity and timeout consistency across all payment fragments. Together, these mechanisms reduce information leakage while preserving robust payment execution under dynamic network conditions. Experimental evaluation on real Lightning Network topologies and synthetic stress scenarios demonstrates that AMP significantly lowers balance disclosure and endpoint inference risk, improves payment completion under skewed liquidity distributions, and introduces only moderate computational and communication overhead. The results indicate that adaptive proof-carrying multipath routing offers a practical and effective direction for building secure, privacy-preserving, and high-success payment channel networks.
A deployed model can appear unchanged while ceasing to be the model it claims to be. Publicly available weight-level mutation toolchains now automate safety-alignment removal from open-weight models on ordinary hardware, producing checkpoints intended to preserve operational familiarity while discarding refusal behavior. This paper argues that safety-alignment removal is a model-identity failure: in tested published checkpoints from multiple toolchains across two model families, the mutation leaves measurable structural scars ranging from 7.6 to over 2,300 times the instrument's acceptance threshold. Artifact identity, workload identity, and agent authorization can all remain valid while structural model identity fails — a finding that the program's formally verified admissibility doctrine predicted before this threat class existed. A sentinel validation panel across four model families confirms that the hardened instrument configuration preserves or improves all tested positives. In an agentic deployment context, model-identity failure propagates upward into agent-integrity failure: the agent is authenticated, but the model inside it is no longer the model the surrounding controls were designed to govern. The practical implication is that runtime evaluation frameworks — including those emerging under the EU AI Act — implicitly depend on a model continuity that weight-level mutation can break, and that structural identity verification offers a candidate evidentiary layer for closing that gap. The Neural Network Identity Series — Mathematical foundations, empirical validation, and governance frameworks for verifying which model is running Newest addition: Technical Note: The Disappearing Window — AI Logprob Access Withdrawal and the Structural Verifiability of Frontier Model Contracts (DOI: 10.5281/zenodo.20362098) Paper 1: The δ-Gene: Inference-Time Physical Unclonable Functions from Architecture-Invariant Output Geometry (DOI: 10.5281/zenodo.18704275) Paper 2: Template-Based Endpoint Verification via Logprob Order-Statistic Geometry (DOI: 10.5281/zenodo.18776711) Paper 3: The Geometry of Model Theft: Distillation Forensics, Adversarial Erasure, and the Illusion of Spoofing (DOI: 10.5281/zenodo.18818608) Paper 4: Provenance Generalization and Verification Scaling for Neural Network Forensics (DOI: 10.5281/zenodo.18872071) Paper 5: Beneath the Character: The Structural Identity of Neural Networks — Mathematical Evidence for a Non-Narrative Layer of AI Identity (DOI: 10.5281/zenodo.18907292) Paper 6: Which Model Is Running?: Structural Identity as a Prerequisite for Trustworthy Zero-Knowledge Machine Learning (DOI: 10.5281/zenodo.19008116) Paper 7: The Deformation Laws of Neural Identity (DOI: 10.5281/zenodo.19055966) Paper 8: What Counts as Proof? — Admissible Evidence for Neural Network Identity Claims (DOI: 10.5281/zenodo.19058540) Paper 9: Composable Model Identity — Formal Hardening of Structural Attestations in the Enterprise Identity Stack (DOI: 10.5281/zenodo.19099911) Paper 10:Where Identity Comes From: Path Sensitivity and Endpoint Underdetermination in Neural Network Training (DOI: 10.5281/zenodo.19118807) Paper 11: Post-Hoc Disclosure Is Not Runtime Proof: Model Identity at Frontier Scale (DOI: 10.5281/zenodo.19216634) Paper 12: Family-Dependent Response to Reasoning Distillation Across Structural and Functional Identity Layers (DOI: 10.5281/zenodo.19298857) Paper 13: Safety-Alignment Removal as a Model-Identity Failure — Structural Evidence from Published Weight-Level Mutation Checkpoints (DOI: 10.5281/zenodo.19383019) Technical Note: Agent Identity Is Not Model Identity (DOI: 10.5281/zenodo.19240883) Technical Note: Gap Invariance: Why PPP Measurements Are Domain-Independent by Construction (DOI: 10.5281/zenodo.19275524) Technical Note: Measured Model Substitution Under Valid Agent Credentials (DOI: 10.5281/zenodo.19342848) Technical Note: Artifact Identity Is Not Runtime Identity — Trustfall Lite and the Boundary of File-Level Model Verification (DOI: 10.5281/zenodo.20019127) Formal Verification Stack for Neural Network Structural Identity (IT-PUF Coq Proofs) (DOI: 10.5281/zenodo.18930621) Copyright (c) 2026 Anthony Ray Coslett / Fall Risk AI, LLC. All Rights Reserved. Confidential and Proprietary. Patent Pending (Applications 63/982,893, 63/990,487, 63/996,680, 64/003,244).
Open access
2 source records
Adversarial Robustness in Machine Learning
Physical Unclonable Functions (PUFs) and Hardware Security
About this paper This paper argues that the conflict between online protection and privacy is not inevitable. The real problem is that most current systems wrongly treat compliance and identity as the same thing. The proposed VI + CJT framework separates them. It allows platforms to receive only the minimum lawful compliance result they need — for example, whether a user falls below the relevant legal age threshold — without learning the child’s name, date of birth, address, biometric profile, or broader identity. In that sense, the paper’s central theme is age verification without surveillance through purpose-bound cryptographic enforcement. How AI Makes the Problem Worse AI makes the children’s online safety problem more serious in three distinct ways. First, it changes exposure from passive to active. Harmful material is no longer merely available on a platform; recommendation and optimisation systems can identify vulnerable users, rank harmful content more aggressively for them, and progressively amplify it based on engagement signals. In that environment, a child is not simply finding harmful content — the system is learning from the child and serving more of it. Second, AI makes weak age-verification methods more dangerous. A false self-declared age is no longer just a wrong entry in a sign-up form. Once accepted, it becomes operational input for recommendation, advertising, and behavioural optimisation systems, which then treat the child as an adult user profile. This means the error is not static; it is continuously acted upon by AI systems that optimise for attention and engagement rather than child protection. Third, AI encourages platforms to solve the problem through more surveillance. In practice, this often means AI-based age estimation using faces, voices, or behavioural patterns. But this approach creates a new harm while claiming to solve another one: it turns child protection into biometric and behavioural monitoring, and can generate datasets that may later be reused for additional profiling or model training. In other words, AI can make age assurance both more intrusive and less accountable. A further difficulty is that AI systems are often opaque even to their operators. As your draft correctly notes, policy rules alone may not be enough, because platforms may not reliably know how their own recommendation systems are treating minors in practice. This is why the problem is not only one of age verification, but also one of enforceable control over AI behaviour. That is precisely why the VI + CJT model matters. It does not ask AI systems to infer age or interpret law for themselves. Instead, it provides a minimal, authoritative compliance signal and machine-readable constraints that can limit recommendation, advertising, and profiling behaviour toward minors without exposing identity. Current Solutions Self-declaration is easily bypassed. A child can simply enter a false age, and the platform’s AI systems then treat that false declaration as valid input for recommendation, targeting, and optimisation. Identity-linked verification creates major privacy risks. When age assurance depends on sharing civil identity information with commercial platforms, the result is unnecessary exposure of family and child data to entities with strong incentives to collect, retain, and monetise it. AI-based age estimation introduces biometric surveillance. Estimating age from face, voice, or behaviour may appear convenient, but it creates new harms by collecting sensitive personal and biometric data as a side effect of child protection. Current systems collapse compliance into identity. What platforms usually need is not the full identity of the user, but only the legally relevant compliance fact. Existing approaches fail because they demand far more data than is necessary for that purpose. Policy rules alone are not enough in AI-driven environments. Even where legal obligations exist, platforms may not reliably translate them into enforceable constraints on opaque recommendation and engagement systems. As a result, compliance may remain declaratory rather than technically enforced. Proposed Solution Use VI + CJT as a purpose-bound cryptographic layer. The framework converts verified civil identity held by trusted authorities into a minimal compliance credential that reveals only the relevant age-threshold result for the applicable jurisdiction. Avoid disclosure of identity data. The credential contains no name, no full date of birth, no address, and no biometric data. Each credential uses a fresh random identifier, making it unlinkable across sessions. Keep the credential under user control. The credential is stored on the user’s device in secure hardware rather than on platform servers, reducing centralised exposure and retention risks. Use zero-knowledge proof for age compliance. When access is requested, the platform receives only a yes-or-no compliance result, without learning the underlying identity attributes or credential contents. Encode law into machine-readable CJTs. The Compliance Jurisdiction Token expresses the applicable legal rules, including jurisdiction-specific age thresholds and AI-related restrictions such as limits on engagement optimisation, advertising targeting, or behavioural profiling for minors. Constrain platform AI without making it identity-aware. Recommendation engines and other AI systems receive only the compliance signal necessary to adjust behaviour for minors, allowing them to become jurisdiction-aware and age-aware without becoming identity-aware. Replace probabilistic AI age estimation with authoritative attestation. Instead of guessing age through opaque models, the framework provides deterministic, government-signed, legally relevant compliance proof. Enable auditability and cross-border enforcement. Regulators can test whether platforms respond correctly to compliance signals, and the applicable child-protection rule can follow the user across borders through jurisdiction-bound credentials and tokens. Core Message The paper’s core message is simple: platforms do not need to know who a child is in order to know what protections the law requires. By separating compliance from identity, the VI + CJT model offers a path to child safety that is enforceable, privacy-preserving, and better suited to AI-driven digital environments.
AIGP-Σ (AI Governance Protocol — Sigma) is a post-quantum cryptographic identity and authorization framework designed for autonomous AI agents operating in multi-agent and agentic payment environments. The protocol suite consists of five interconnected specifications: WP-01: Core Protocol — ML-DSA (CRYSTALS-Dilithium) based identity anchoring with STARK zero-knowledge proofs via RISC0, Bitcoin blockchain timestamping, and a cryptographic Kill Switch mechanism for emergency AI halt. WP-02: Kill Switch — Formal specification of the HALT proof system enabling verifiable, tamper-proof shutdown of AI agents without revealing operational state. WP-03: SSL for Agents — A mutual TLS-equivalent handshake protocol adapted for AI agent-to-agent communication, providing forward secrecy and post-quantum resistance. WP-04: Agentic Payments — Authorization layer for autonomous financial transactions executed by AI agents, with cryptographic scope limitation and audit trails. WP-05: Multi-Agent Orchestration — Trust propagation and delegation model for hierarchical multi-agent systems with verifiable credential chains.
Java applications are prone to vulnerabilities stemming from the insecure use of security-sensitive APIs, such as file operations enabling path traversal or deserialization routines allowing remote code execution. These sink APIs encode critical information for vulnerability discovery: the program-specific constraints required to reach them and the exploitation conditions necessary to trigger security flaws. Despite this, existing fuzzers largely overlook such vulnerability-specific knowledge, limiting their effectiveness. We present GONDAR, a sink-centric fuzzing framework that systematically leverages sink API semantics for targeted vulnerability discovery. GONDAR first identifies reachable and exploitable sink call sites through CWE-specific scanning combined with LLM-assisted static filtering. It then deploys two specialized agents that work collaboratively with a coverage-guided fuzzer: an exploration agent generates inputs to reach target call sites by iteratively solving path constraints, while an exploitation agent synthesizes proof-of-concept exploits by reasoning about and satisfying vulnerability-triggering conditions. The agents and fuzzer continuously exchange seeds and runtime feedback, complementing each other. We evaluated GONDAR on real-world Java benchmarks, where it discovers four times more vulnerabilities than Jazzer, the state-of-the-art Java fuzzer. Notably, an earlier GONDAR version contributed to Team Atlanta's first-place CRS in the DARPA AI Cyber Challenge, and is integrated into OSS-CRS, a sandbox project in The Linux Foundation's OpenSSF, to analyze open-source Java projects, where it has already uncovered a zero-day vulnerability.
We present a unified dynamical framework for the nontrivial zeros of the Riemann zeta function, integrating three perspectives: (i) the de Bruijn–Newman flow and its reduction to a logarithmic Coulomb gas, (ii) a renormalization group information flow from the 2C Theory, and (iii) spectral compression in 2D Dirac systems under strong magnetic fields. Through an iterative discovery process — connecting existing knowledge, identifying new principles at the intersection, then connecting those principles with prior knowledge to discover deeper ones — we identify three structural contributions: (1) The Disorder–Order Paradox: the irregularity of the prime distribution generates the information restoring force (curvature V''(1/2) = π²/8) that confines zeros to the critical line Re(s) = 1/2. (2) The Universal Irreversibility Threshold: the critical value C = 2/3, independently derived in D.S. Theory (holographic ratio β = 3/2), the 2C Theory (RG flow fixed point), and Lowest Landau Level physics (spectral weight threshold for forced Landauer erasure), marks the point at which one-dimensional spectral reduction becomes irreversible. (3) The Entropic Barrier: the information free energy V(σ) possesses a barrier surrounding σ = 1/2 whose height grows with integrated prime density, forbidding zero escape once the critical threshold is exceeded. We formulate one precisely stated open problem: proving that the entropic barrier height diverges as T → ∞, which is equivalent to establishing an L² + entropy → L∞ inequality for the equilibrium measure of the logarithmic gas. The framework connects analytic number theory, information theory, renormalization group methods, and condensed matter physics within a single coherent structure. This paper is a structural framework proposal, not a proof of the Riemann Hypothesis. The iterative discovery methodology is inspired by the WillCore simulation platform.
This study presents ZK-EHR, a decentralized access control framework designed to enable secure and privacy-preserving sharing of encrypted electronic health records across institutional boundaries. Unlike existing blockchain-based EHR access control systems that expose user identities on-chain or lack cryptographic privacy guarantees, ZK-EHR decouples authorization from identity disclosure by integrating zk-SNARK-based proofs with blockchain smart contracts to verify policy compliance without revealing user roles, affiliations, or credentials. The framework employs three differentiated actor roles—Patient (Data Owner), Doctor (Care Provider), and Researcher (Authorized Analyst)—with distinct policy-driven access workflows, a custom Groth16 zero-knowledge circuit for role-based constraint enforcement, and a modular architecture combining on-chain verification with off-chain encrypted storage via IPFS. Concrete design proposals for access revocation and replay attack prevention are introduced to address operational security requirements. The system was evaluated under multiple operational and adversarial scenarios. Experimental results indicate consistent on-chain verification latency (approximately 390 ms), reliable rejection of tampered submissions, and per-verification gas consumption of 216,631 gas. A comparative analysis against representative baseline systems demonstrates that ZK-EHR uniquely combines identity anonymity, on-chain cryptographic policy enforcement, and auditable encrypted record retrieval. These findings establish the feasibility of zk-SNARK-based access control for decentralized, verifiable, and privacy-aware EHR management.
Margherita Cozzolino, Stephan Krenn, Thomas Lorünser
While QKD ensures information-theoretic security at the link level, real-world deployments depend on trusted repeaters, creating potential vulnerabilities. In this paper, we thus introduce a topology-hiding connectivity assurance protocol to enhance trust in quantum key distribution (QKD) network infrastructures. Our protocol allows network providers to jointly prove the existence of a secure connection between endpoints without revealing internal topology details. By extending graph-signature techniques to support multi-graphs and hidden endpoints, we enable zero-knowledge proofs of connectivity that ensure both soundness and topology hiding. We further discuss how our approach can certify, e.g., multiple disjoint paths, supporting multi-path QKD scenarios. This work bridges cryptographic assurance methods with the operational requirements of QKD networks, promoting verifiable and privacy-preserving inter-network connectivity.
This paper describes a zero-knowledge proof system that enables verification of password policy compliance within an asymmetric password-authenticated key exchange (aPAKE) protocol specifically OPAQUE (RFC 9807) without revealing the password to the server. The system is built on a composable sub-circuit architecture: independent verification gadgets are combined into a single zero-knowledge proof, each gadget accepting portions of the private witness and producing public instance values, enabling the server to verify multiple password properties in one proof verification. Four gadgets are disclosed: (1) a Policy Engine for character class verification via lookup tables, (2) a History Nullifier for password inequality proof via squared-difference accumulation, (3) an OPAQUE Binder for cryptographic binding to the aPAKE registration element via hash-to-curve and elliptic curve scalar multiplication, and (4) a Breach Detector for offline breached-password detection via Bloom filter non-membership proof using algebraic hashing. The composable architecture permits addition of further gadgets without modifying existing ones, each extending the public instance vector.
Machine Law Engine (MLE) v1.2.0 presents a formal computational architecture that reconceives regulatory compliance from a retrospective, documentary discipline into a pre-emptive, cryptographically enforced state property. Where classical GRC tooling observes violations after they occur, the MLE enforces legal constraints before execution — making non-compliant operations computationally impossible rather than merely detectable. The architecture introduces three original contributions to the field of computational law and applied cryptography: (1) The Admissibility Vector — a four-dimensional formal scoring function (authority α, evidence ε, context γ, transition legality τ) that evaluates every regulated operation at execution time against all applicable legal rules. The collapse axiom τ=0 → Φ=0 produces terminal refusals for legally impossible state transitions that cannot be overridden by any combination of authority or evidence. (2) The Challenger Provenance Architecture — a novel mechanism, without precedent in published GRC frameworks, that enforces structural independence of AI-assisted compliance reasoning. If a challenger input cannot demonstrate cryptographic divergence (CPD ≥ 0.70, path_overlap ≤ 0.20) from the primary reasoning path, the gate cannot achieve full institutional binding — operationalising DORA Art.15, EU AI Act Art.9(9), and BCBS 239 Principle 11 as cryptographic invariants rather than policy obligations. (3) The Seven Formal Invariants — hard computational constraints governing the MLE's correctness properties, with mathematical predicates, three-tier runtime monitoring (write-time, scheduled, continuous), and automated violation response protocols including cryptographically evidence-hashed remediation workflows. The reference implementation integrates: four hardware TEE providers (AWS Nitro Enclave, Azure Confidential Computing, Intel SGX/TDX, AMD SEV-SNP) with PCR register semantic attestation; a post-quantum cryptographic stack fully standardised under NIST FIPS 203/204/205 (CRYSTALS-Kyber-1024, CRYSTALS-Dilithium-3, SPHINCS+) providing 30-year evidence integrity against harvest-now-decrypt-later attacks; four PLONK-based Zero-Knowledge proof circuits on BLS12-381 (128-bit soundness) resolving privacy-compliance paradoxes for OFAC sanctions screening, FinCEN BSA threshold verification, DORA Art.28 vendor certification, and GDPR right-to-erasure evidence chains; a bi-temporal append-only ledger with DORA Art.11 automated retro-simulation; a seven-stage NLP-to-enforcement-code compilation pipeline with Kyber-1024 tamper detection and dual-approval protocol; a multi-framework conflict engine covering six active cross-regulatory conflict pairs (GDPR × FINMA, GDPR × FinCEN BSA, DORA × NIS2, EU AI Act × GDPR, eIDAS 2 × CCPA) with five deterministic resolution strategies; and nine Interactive Verification Layer modules enabling complete live regulatory demonstration in 35 minutes without preparation. Regulatory framework coverage spans 17 frameworks across EU, US, CH, and UK jurisdictions including DORA, GDPR, NIS2, EU AI Act, eIDAS 2, FINMA Circ.2023/1, BaFin MaRisk, FinCEN BSA, OFAC/CAATSA, FATCA, CRS, ISO 27001:2022, and SOC 2. Evidence export targets eight regulatory authorities (EBA, EDPB, ENISA, FINMA, BaFin, FCA, SEC, FinCEN) in authority-native formats (XBRL, XML, BSA E-Filing) via Dilithium-3-signed, SPHINCS+-sealed bundles with direct API transmission. The system is currently deployed in production as of 31 March 2026. Invariant status at publication: 6/7 HOLDING · INV-5 WARNING (AMD SEV-SNP PCR2 drift, remediation active, resolution within 72 hours). Keywords: machine law, pre-emptive compliance enforcement, admissibility vector, post-quantum cryptography, trusted execution environment, zero-knowledge proofs, bi-temporal ledger, DORA, GDPR, EU AI Act, cryptographic compliance, challenger provenance, regulatory technology, GRC, hardware attestation, CRYSTALS-Kyber, CRYSTALS-Dilithium, SPHINCS+, PLONK License: CC BY 4.0 Version: 1.2.0 DOI: 10.5281/zenodo.immo.quickCore.1.2.0
Threshold transactions in Bitcoin is an effective solution for vulnerability of wallets to the loss or compromise of secret keys. It also enhances the applicability of Bitcoin to include use-cases that require partitioning the trust among a set of parties. Currently, the threshold transactions on Bitcoin expose the actual signers within the group of participants. This poses a threat of wallet hacks or theft targeting these signers. To address this issue of privacy, we propose a novel protocol to create threshold transaction using a combination of on-chain locking and off-chain proof of knowledge. As Bitcoin currently does not support verification of zero-knowledge schemes, the proposed protocol uses a Trusted Third Party ( TTP ) to verify the proofs off-chain. The trust on the third party is only limited to its service of signing on behalf of the users. The main contribution is the development and applicability of a m-out-of-N proof of partial knowledge that maintains the privacy of the signers both on-chain from the transaction verifiers and off-chain from the TTP and other signers as well. The protocol leverages Taproot’s spending path flexibility to incorporate dual spending capabilities and employs off-chain zero knowledge Σ-protocols to prove knowledge of private keys without disclosing their associated public keys. Experimental analysis demonstrates improved scalability and privacy than the mainstream threshold signature schemes for Bitcoin. A formal analysis demonstrates and establishes the security goals of the proposed mechanism.
The current methods don't meet the security and performance needs of Internet of Vehicles (IoV) apps, and they also don't give the end user a low-latency, secure edge-computing service at the same time, while in the context of vehicles. This study presents a blockchain-enabled edge computing architecture that employs Double Deep Q-Network (DDQN) for reinforcement learning and lightweight Practical Byzantine Fault Tolerance (PBFT) for consensus, aiming to simultaneously enhance latency, energy efficiency, and security. The containerised architecture uses Hyperledger Fabric with Kubernetes to efficiently manage micro-services and move tasks off of them. In urban, suburban, and highway settings, the framework consistently outperforms baseline algorithms, with a 30–45% improvement in end-to-end latency and a 55% reduction in energy use under moderate to heavy loads. The system finished more than 95% of its tasks while keeping block consensus times under 1.2 seconds at peak loads. The architecture also showed consistent performance with different levels of vehicle density and used zero-knowledge proofs with attribute-based security to protect data from cyber threats from bad actors. These findings indicate that the integration of DDQN and blockchain will mitigate security issues in the Internet of Vehicles (IoV) by enabling secure edge computing for future vehicular networks.
We present HyperVerITAS, a new zero-knowledge proof (ZKP) system for image provenance that enables scalable, efficient, and privacy-preserving verification of image transformations. HyperVerITAS builds upon the same minimal trust model as VerITAS (IEEE S&P '25), requiring trust only in the image source device, while treating the editing software as untrusted. Unlike VerITAS, which relies on FFT-intensive SNARKs and suffers from high memory overhead (up to 120 GB), HyperVerITAS leverages multilinear polynomial encodings over the Boolean hypercube to dramatically reduce both proving time and memory usage. Our design cleanly separates signature verification from image transformation, supports modular integration of multiple polynomial commitment schemes (including post-quantum constructions) and naturally extends to a wide range of affine image transformations. We implement HyperVerITAS with two distinct commitment schemes (Brakedown and multilinear KZG) and evaluate it on full-system pipelines involving cropping and grayscaling. On commodity hardware (Apple M3, 36 GB RAM), HyperVerITAS generates proofs for 33 MP images using only 27 GB of RAM and 6.6 minutes of proving time, whereas VerITAS fails to scale beyond 4 MP. These results establish HyperVerITAS as a practical and scalable ZKP system for secure and efficient image provenance.
Federated unlearning enables clients to withdraw their contributions from a global model.However, enabling clients to verify whether the server has honestly and effectively removed their contributions remains a critical challenge. To address this aspect, which has been largely overlooked in existing literature, a verification model based on zero-knowledge proofs was constructed, and a comprehensive framework for verifiable federated unlearning was proposed. Combined with a dynamically updated Merkle tree structure, a novel verifiable federated unlearning scheme was presented characterized by its zero-knowledge property. This allows for the efficient generation of cryptographic proofs for server unlearning operations while rigorously protecting the data privacy of other clients. We evaluate the effectiveness and computational overhead of the proposed scheme. Comparative experiments with Rivest-Shamir-Adleman (RSA) accumulator-based and Hash chain-based schemes demonstrate that, when the model parameter size reaches the order of <inline-formula><alternatives><math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"><msup><mrow><mn mathvariant="normal">10</mn></mrow><mrow><mn mathvariant="normal">5</mn></mrow></msup></math><graphic specific-use="big" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/B6D6E598-14B1-468e-9A32-73199F9CD69E-M002.jpg"><?fx-imagestate width="4.23333359" height="2.53999996"?></graphic><graphic specific-use="small" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="alternativeImage/B6D6E598-14B1-468e-9A32-73199F9CD69E-M002c.jpg"><?fx-imagestate width="4.23333359" height="2.53999996"?></graphic></alternatives></inline-formula>, the proposed scheme improves proof generation speed by approximately two orders of magnitude and verification speed by 13.2 times compared to the RSA-based scheme. Furthermore, it effectively avoids the scalability bottleneck of data linear growth in verification overhead inherent in Hash chain-based schemes.
Three model substitution scenarios were executed against a live inference endpoint with real HTTP requests, signed attestation JWTs, and OPA policy enforcement. In each scenario, every tested workload, artifact, or API identity control relevant to that scenario — workload JWT validation, health checks, gateway process continuity, artifact manifest integrity, API key authentication — remained valid while the model changed. In each scenario, a structural identity measurement based on activation geometry during a standard forward pass detected the substitution and the enforcement layer denied the request. Three substitutions were tested and three were detected, with zero false accepts in this run. The warm-path verification latency was 5.7–6.7 seconds on a single A100 with the model already loaded. The complete evidence chain — before/after measurement results, attestation claim summaries, OPA policy evaluations, and HTTP response codes — is published alongside this note as machine-readable JSON. This is a technical note, not a numbered entry in the research series. Supplementary Material. This note is accompanied by three machine-readable evidence files: cat3_results.json (structured results for all three scenarios, including the full before/after evidence chain for Scenario A with signed attestation claims, OPA policy evaluations, and HTTP response codes), manifest_authorized.json (SHA-256 build manifest for the enrolled model, 10 files, all verified), and manifest_substituted.json (SHA-256 build manifest for the substituted model, 10 files, all verified). All three files are available for download as supplementary files attached to this record. The Neural Network Identity Series — Mathematical foundations, empirical validation, and governance frameworks for verifying which model is running Newest addition: Technical Note: The Disappearing Window — AI Logprob Access Withdrawal and the Structural Verifiability of Frontier Model Contracts (DOI: 10.5281/zenodo.20362098) Paper 1: The δ-Gene: Inference-Time Physical Unclonable Functions from Architecture-Invariant Output Geometry (DOI: 10.5281/zenodo.18704275) Paper 2: Template-Based Endpoint Verification via Logprob Order-Statistic Geometry (DOI: 10.5281/zenodo.18776711) Paper 3: The Geometry of Model Theft: Distillation Forensics, Adversarial Erasure, and the Illusion of Spoofing (DOI: 10.5281/zenodo.18818608) Paper 4: Provenance Generalization and Verification Scaling for Neural Network Forensics (DOI: 10.5281/zenodo.18872071) Paper 5: Beneath the Character: The Structural Identity of Neural Networks — Mathematical Evidence for a Non-Narrative Layer of AI Identity (DOI: 10.5281/zenodo.18907292) Paper 6: Which Model Is Running?: Structural Identity as a Prerequisite for Trustworthy Zero-Knowledge Machine Learning (DOI: 10.5281/zenodo.19008116) Paper 7: The Deformation Laws of Neural Identity (DOI: 10.5281/zenodo.19055966) Paper 8: What Counts as Proof? — Admissible Evidence for Neural Network Identity Claims (DOI: 10.5281/zenodo.19058540) Paper 9: Composable Model Identity — Formal Hardening of Structural Attestations in the Enterprise Identity Stack (DOI: 10.5281/zenodo.19099911) Paper 10:Where Identity Comes From: Path Sensitivity and Endpoint Underdetermination in Neural Network Training (DOI: 10.5281/zenodo.19118807) Paper 11: Post-Hoc Disclosure Is Not Runtime Proof: Model Identity at Frontier Scale (DOI: 10.5281/zenodo.19216634) Paper 12: Family-Dependent Response to Reasoning Distillation Across Structural and Functional Identity Layers (DOI: 10.5281/zenodo.19298857) Paper 13: Safety-Alignment Removal as a Model-Identity Failure — Structural Evidence from Published Weight-Level Mutation Checkpoints (DOI: 10.5281/zenodo.19383019) Technical Note: Agent Identity Is Not Model Identity (DOI: 10.5281/zenodo.19240883) Technical Note: Gap Invariance: Why PPP Measurements Are Domain-Independent by Construction (DOI: 10.5281/zenodo.19275524) Technical Note: Measured Model Substitution Under Valid Agent Credentials (DOI: 10.5281/zenodo.19342848) Technical Note: Artifact Identity Is Not Runtime Identity — Trustfall Lite and the Boundary of File-Level Model Verification (DOI: 10.5281/zenodo.20019127) Formal Verification Stack for Neural Network Structural Identity (IT-PUF Coq Proofs) (DOI: 10.5281/zenodo.18930621) Copyright (c) 2026 Anthony Ray Coslett / Fall Risk AI, LLC. All Rights Reserved. Confidential and Proprietary. Patent Pending (Applications 63/982,893, 63/990,487, 63/996,680, 64/003,244).
Nonnegative matrix factorization (NMF) approximates a nonnegative matrix, $X$, by the product of two nonnegative factors, $WH$, where $W$ has $r$ columns and $H$ has $r$ rows. In this paper, we consider NMF using the component-wise L1 norm as the error measure (L1-NMF), which is suited for data corrupted by heavy-tailed noise, such as Laplace noise or salt and pepper noise, or in the presence of outliers. Our first contribution is an NP-hardness proof for L1-NMF, even when $r=1$, in contrast to the standard NMF that uses least squares. Our second contribution is to show that L1-NMF strongly enforces sparsity in the factors for sparse input matrices, thereby favoring interpretability. However, if the data is affected by false zeros, too sparse solutions might degrade the model. Our third contribution is a new, more general, L1-NMF model for sparse data, dubbed weighted L1-NMF (wL1-NMF), where the sparsity of the factorization is controlled by adding a penalization parameter to the entries of $WH$ associated with zeros in the data. The fourth contribution is a new coordinate descent (CD) approach for wL1-NMF, denoted as sparse CD (sCD), where each subproblem is solved by a weighted median algorithm. To the best of our knowledge, sCD is the first algorithm for L1-NMF whose complexity scales with the number of nonzero entries in the data, making it efficient in handling large-scale, sparse data. We perform extensive numerical experiments on synthetic and real-world data to show the effectiveness of our new proposed model (wL1-NMF) and algorithm (sCD).
Cross-domain data exchange is an important technical approach for realizing the value of data assets. However, lacking a single trusted root CA across domains, cross-domain schemes often encounter difficulties in authentication, controlled data flow, and fine-grained authorization. We propose a cross-domain data sharing scheme that uses decentralized identifiers and threshold proxy re-encryption. This scheme adopts the intra-domain leader node to verify the user identity, and the inter-domain multi-agent nodes collaborate in a threshold manner to handle cross-domain registration requests and re-encryption requests. Through threshold cooperation, the problem of single point of failure is effectively solved. The hash value of cross-domain registration information is stored on the blockchain, leveraging the immutable and traceable characteristics of blockchain to achieve trusted cross-domain data sharing. In addition, we introduce a ciphertext version tag to enable fast updates of re-encryption keys and use zero-knowledge proofs to verify re-encrypted ciphertext correctness. The security analysis indicates that our scheme has IND-CCA2 security under the DBDH assumption and can effectively resist collusion attacks. Performance analysis shows that our scheme is efficient, and can better meet the needs of cross-domain data sharing.
Contemporary cryptographic execution systems-particularly those employing zero-knowledge proofs-provide strong guarantees that a computation satisfies a given arithmetic circuit. However, satisfying a circuit is not equivalent to executing correctly with respect to the intended semantics of the system being proven. This paper identifies and formalizes the semantic gap: the class of failures in which execution is provably valid under a proof system yet provably invalid under the system's formal specification. We present the Verifiable Semantic Execution Layer (VSEL), a layered architecture that binds formal specification, execution, constraint derivation, proof generation, and verification into a single semantically coherent pipeline. VSEL models systems as deterministic labeled transition systems, defines explicit semantic mappings between concrete and formal artifacts, derives constraints mechanically from a semantic intermediate representation, and requires that every accepted proof attest not merely to constraint satisfaction but to membership in the formal language of valid execution traces. We define the proof obligations, invariant system, and refinement chain required for end-to-end semantic correctness; characterize the adversarial model including specification manipulation, underconstraint exploitation, and compositional failure; and establish the conditions under which composition of independently correct systems preserves global correctness. The architecture integrates hybrid post-quantum cryptography to ensure long-term validity of proofs and commitments, and introduces a formal economic invariant layer that elevates economic semantics from informal domain knowledge to enforceable first-class predicates over states and execution traces. We provide a complete formal treatment of the system model, semantic preservation theorems, constraint soundness and completeness conditions, witness uniqueness requirements, economic admissibility conditions, and the assume-guarantee framework for safe composition.
Open access
2 source records
Cryptographic Implementations and Security
Physical Unclonable Functions (PUFs) and Hardware Security