Blockchain Papers

Alaa Alqaryuti, Haya Aljaghoub, Khaled Salah, Ahmad Mayyas

The growing adoption of Proton Exchange Membrane (PEM) fuel cell electric vehicles (FCEVS) has increased the need for secure, transparent, and verifiable certification and lifecycle tracking of hydrogen-related components. Current practices rely on fragmented documentation and centralized record-keeping, which creates risks of data manipulation, incomplete maintenance histories, and limited visibility for regulators and service providers. This paper introduces a blockchain-based framework that integrates decentralized storage, oracle-driven automation, and three interoperable smart contracts to manage stakeholder registration, component certification, vehicle assembly validation, and maintenance tracking. Implemented and evaluated in an EVM-compatible environment, the system enforces strict role-based access control, generates immutable audit trails, and automates both failure-based and mileage-based maintenance triggers using real-time inputs. A gas-cost analysis demonstrates that all contract functions operate at minimal cost under current Ethereum conditions, supporting the feasibility of real-world deployment. Overall, the proposed framework improves traceability, regulatory compliance, and operational accountability by enabling near real-time verification of certification records and reducing manual audit processing steps compared to traditional document-based certification workflows. • Blockchain ensures secure, tamper-proof FCEV component traceability. • Smart contracts automate certification, assembly, and maintenance. • Oracle triggers enable real-time, failure-, and scheduled service. • Framework improves compliance, transparency, and lifecycle oversight.

Antonio José Marín Soto

We establish an information-theoretic lower bound on the prover overhead of any zero-knowledge proof system that verifies arbitrary neural network inference. We prove a minimum multiplicative overhead of 2x for general circuits, rising to 4x for neural networks with ReLU activations due to activation encoding, weight commitment, and layer dependency costs. We further prove that composing ZK with fully homomorphic encryption produces multiplicative overhead blowup, making ZK+FHE verification impractical beyond approximately 10^4 gates. We survey six contemporary proof systems and show their observed overheads are consistent with our bounds. Our results formalize the intuition that free verification of AI computation is impossible and provide concrete bounds for system designers.

Anthony Coslett

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).

Mayckon Giovani

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.

PRAKASH VAITHYANATHAN

Current synchronous AI architectures, exemplified by the 1000W+ NVIDIA Rubin platform, rely on global clock-trees that generate deterministic electromagnetic harmonics. These periodic power signatures act as physical beacons, enabling sophisticated Side Channel Power Analysis (SCPA) to reconstruct sensitive model weights. This paper proposes the Asynchronous Entropy-Engine (AEE), a theoretical clockless execution environment that replaces rhythmic switching with handshake-driven logic to eliminate exploitable leakage. Central to this architecture is the Arnold Stability Index (ASI) Governor, which mapsregister-level neural trajectories onto high-dimensional stability manifolds to trigger Dynamic Grid-Coarsening. Architectural modeling indicates this approach achieves a 30.5% reduction in the ”Synchronous Polling Tax.” Crucially, we introduce a Globally Asynchronous Locally Synchronous (GALS) interface, wherein synchronous logic islands are triggered by an asynchronous handshake protocol governed by the ASI to mask periodic power-draw harmonics. We demonstrate through performance analysis that the resulting energy surplus can power a hardware-integrated Zero-Knowledge Proof (ZKP) generator, producing non-interactive STARKs of inference integrity without a net power penalty. Simulation results indicate a 98.9% reduction in deterministic harmonics, effectively rendering high-TDP silicon ”electronically silent.” By decoupling execution from a fixed global heartbeat, the AEE establishes a new paradigm of ”Energy-Neutral Privacy,” providing a robust physical-layer defense against adversarial power analysis in trillion-parameter AI factories.

Brandon Husbands, Witchborn Systems

Tangible Encryption is a cryptographic framework that replaces the “secret zero” bootstrap problem in secrets management with a verifiable, identity-based trust model. Instead of requiring an antecedent credential to access protected secrets, this approach binds access control to ownership of a persistent cryptographic token (e.g., an NFT), enabling authentication through proof of ownership rather than shared knowledge. This work formalizes the use of non-fungible tokens as ownable roots of trust, where token ownership encodes identity, access rights, and provenance on a distributed ledger. A deterministic key derivation model is introduced, allowing secrets to be encrypted and decrypted without transmitting or storing a traditional master secret. Verification is performed via cryptographic signatures and on-chain state checks, eliminating circular trust dependencies inherent in systems such as Vault, SOPS, and cloud KMS. The framework is evaluated in the context of AI systems, including model provenance, secure dataset access, and autonomous agent authentication across organizational boundaries. Security considerations such as key compromise, revocation, and ledger integrity are analyzed, alongside implementation tradeoffs between public and permissioned ledgers. Tangible Encryption establishes a portable, verifiable trust anchor that operates independently of any single platform or identity provider, unifying identity, access control, and auditability into a single cryptographic primitive.

Seung Kwon Lee, Seok Bin Son, Joongheon Kim, Hoh Peter In

Quantum machine learning (QML) has attracted growing interest for their ability to achieve superior performance with significantly fewer parameters. However, the high cost and scarcity of current hardware push inference to cloud-hosted quantum devices, creating a tension between verifiability and confidentiality. This work proposes a novel framework that converts quantum neural network operations into classical arithmetic circuits that faithfully approximate genuine quantum computations. By encrypting these circuits with zero-knowledge proofs, it ensures computational validity while concealing internal parameters. Experimental results show that our classical circuits achieve fidelity above 0.9996 and total variation distance below 1% compared to actual quantum computations, verifying the practicality of trustworthy and privacy-preserving quantum inference.

Anthony Coslett

Neural networks deployed behind APIs or in cloud infrastructure are often verifiable only as black boxes. zkML systems have made substantial progress on computational integrity: proving that a committed model produced a claimed output honestly. But those proofs begin from a weight commitment, and a weight commitment is not a model identity. A prover can commit to arbitrary weights, execute them honestly, and still prove the computation correctly. We present an identity-first verification framework for the missing layer beneath computational integrity. The framework composes four levels. Two are inherited: structurally attestable model fingerprints via the IT-PUF protocol, formally verified in Coq and validated across 23 models with zero false acceptances, and hardware-attested binding from fingerprinted identity to model weights through a trusted execution environment. Two are new: a hybrid verifier-checkable computation path through a complete Transformer decoder layer, combining zero-knowledge circuit proofs with deterministic verifier-side checks under incrementally verifiable computation, and output binding from the verified computation to an observable token logit. On a tested micro-model, a one-step recurrence experiment found costs consistent with linear layer scaling: the dominant sub-computation of a second decoder layer matched the first in constraint count and proof size, and layer-boundary normalization acted as a measured scale reset. An accidental rescaling error then compressed the fingerprint observable to roughly 1.5 bits of dynamic range, yet the structural fingerprint retained 0.98 rank correlation with its reference. This suggests that the identity observable may depend more on relational geometry than on activation magnitude. Existing zkML systems address the computation question. This work advances the missing identity layer beneath it. Throughout the paper, formally proved results, empirical validation, and single measured observations are distinguished as [PROVEN], [VALIDATED], and [MEASURED] respectively. 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).

Mingjun Liu, Huiying Li, Ali Muqtadir, Rubab Osama · 5 authors

As Decentralized Finance (DeFi) and Non-Fungible Tokens (NFTs) expand, self-custody wallets have become the primary interface for user sovereignty. However, existing solutions suffer from critical limitations, including static authentication frameworks that compromise usability, a lack of real-time risk awareness, and inadequate key recovery mechanisms that often lead to permanent asset loss or reliance on centralized custodians. Furthermore, current wallets frequently expose transaction metadata, undermining user privacy. To address these systemic flaws, we present a modular self-custody wallet that incorporates a context-aware risk engine for real-time transaction scoring, risk-based adaptive authentication, and a dual-path decentralized key-recovery layer combining DAO-governed Shamir secret sharing with a zk-SNARK-verified fallback. The architecture further includes programmable policy enforcement and a zero-knowledge swap layer with stealth addressing to decouple front-end activity from on-chain data. The design integrates smart contracts on EVM chains and Solana through provider adapters and executes on-device ML inference to minimize latency. Experimental results demonstrate that the proposed system reduces privacy leakage probability to 5% (compared to 85% in standard architectures) and accelerates key recovery from over 24 h to approximately 8 seconds using zk-SNARKs, all while achieving 93.6% risk classification accuracy. The proposed CAPPR-Wallet advances self-custody by combining context adaptivity, privacy, and recoverability without centralized trust.

B. Siva Ganesh, Aditya Basantia, Soumya Sambit Mishra, Jagdish Behera · 5 authors

Healthcare systems are essential for patient care and data management but face persistent challenges with data security, interoperability, and transparency. Traditional centralized storage models increase data breach risks and limit patients’ control over personal health information, complicating seamless data sharing across providers. However, centralized storage systems still lack the security and interoperability required for robust data sharing. To address this, our study proposes a ZKP-based verification system integrated with NFT blockchain technology, aimed at enhancing identity verification while ensuring data privacy and patient control. In our method, NFTs serve as unique digital identifiers linked to patient records, while zero-knowledge proofs (ZKPs) confirm data ownership without disclosing sensitive information. Our findings indicate that this approach mitigates identity fraud risks, strengthens data security, and offers a patient-centered system for selective data access. Beyond patient records, our solution supports transparency in clinical trials and pharmaceutical supply chains, combating counterfeiting and improving quality control. In our paper, we proposed a ZKP-based verification system integrated with NFT blockchain technology to improve identity verification in healthcare, offering a robust, patient-centered approach to data security and integrity.

Noah Erlwein

We introduce inference receipts—lightweight cryptographic commitment records generated during generative AI inference that bind model identity, sampling configuration, and output tokens into a tamper-evident artifact. Unlike zero-knowledge proof systems or trusted execution environments, inference receipts operate under an honest-emitter trust model analogous to Certificate Transparency: the emitter commits faithfully, and any deviation is detectable by third-party auditors. This design occupies a distinct point on the cost–trust Pareto frontier—negligible overhead and no specialized hardware, at the cost of weaker guarantees than cryptographic proofs. We formalize three security properties (receipt binding, tamper detection, chain integrity) via game-based reductions to standard cryptographic assumptions (collision resistance, second-preimage resistance). We describe receipt granularity levels (per-session, per-forward-pass, and per-token), a four-phase orchestration pattern (PLAN, SENSE, DECIDE, PROVE) for bounded AI autonomy, and an oracle mode for opaque cloud models. Ten experiments spanning four model families (1.5B–72B parameters), three quantization levels, three cloud APIs, and three receipt granularity levels on consumer-grade hardware demonstrate: overhead below 0.006% of inference time even at per-token granularity with top-k logit hashing (decreasing to below 0.001% at 72B scale); O(1) amortized chain emission sustained to 10⁶ receipts at 168,860 receipts/sec; 100% tamper detection across 1,200 attempts with zero false positives; perfect within-quantization deterministic replay; and 96% claim recall with 100% chain integrity across 15 multi-step PLAN/SENSE/DECIDE/PROVE workflows, with an honest assessment of gate limitations at 7B model scale. All data, scripts, and a standalone verifier are provided as ancillary files.

Aatu Isopahkala

Our main technical contribution is Observation Algebra Relativity (Theorem 2): a metatheorem formalising that security and robustness predicates are indexed to observation algebras and do not transfer across algebra boundaries. As an application framework, we present the Access Collapse Theorem: a typed structural result showing that direct operational access to the complete state of any system — physical, formal, or social — necessarily collapses at least one of two invariants: operational separateness (d) or scale separation (s). When either invariant reaches zero the access operation does not become inaccurate — it becomes a type error: the predicate is no longer typed to the system being operated. The framework is applied to six instantiations: Planck-scale measurement, zero-knowledge proofs, side-channel attacks, multi-party computation, adversarial explainability, and machine learning model extraction. A Non-Universality Proposition explicitly bounds the framework's scope. A Collapse Diagnostic provides a practical checklist for identifying collapse boundaries in concrete systems. A practical application framework building on this theoretical work is presented in:Isopahkala (2026) – Epistemic Hygiene in Practice.

Basker Palaniswamy, Raveendra Babu Ponnuru, Khondokar Fida Hasan, Paolo Palmieri · 9 authors

No abstract is available for this record.

Li, Y.Y.N.

Every standard signature scheme enforces one property: only the key holdercan sign. What the key holder signs is unconstrained. Policy enforcement-- spending limits, rate limits, access control -- lives in smartcontracts, middleware, or governance: layers that can be upgraded,bypassed, or exploited. We call this the software-layer assumption:compliance holds only if the enforcing code is correct and unmodified. We eliminate this assumption. We introduce behavior-bound signatures(BBS), in which a policy constraint delta(x) < epsilon is committed atkey generation and enforced inside the signature's zero-knowledge proof.If the action violates the policy, the ZK constraint system isunsatisfiable -- no witness, no proof, no signature. This is not asoftware check. It is a mathematical impossibility. No software canoverride. Unlike policy-based signatures (where an authority imposes policy onsigners), BBS is self-committed: the signer binds their own futurebehavior at key generation, and even the signer cannot later violate orrevoke this commitment. We formalize this as policy-soundness (PS-CMA), a security modelstrictly stronger than EUF-CMA, and prove it under standard assumptions(Pedersen binding, Poseidon CR, ZK knowledge soundness). From thissingle primitive, five independent consequences follow -- not as separatedesigns, but as necessary implications of one cryptographic root: (A) Compliance safety under f <= n-1 Byzantine faults, decoupled from honest-quorum assumptions.(B) O(1) verification and audit via a single ZK check and Pedersen homomorphic aggregation.(C) Elimination of the virtual-machine execution layer for policy-constrained transactions.(D) A gasless ledger: branch C removes metering, while ZK-encoded rate limits make spam mathematically nonexistent.(E) The first cryptographic guarantee that a compromised autonomous AI agent cannot exceed its authorized behavioral envelope.

George Chidera Akor, Love Allen Chijioke Ahakonye, Jae Min Lee, Dong-Seong Kim

Zero-knowledge machine learning (ZKML) enables verifiable inference on private data, but deploying convolutional neural networks (CNNs) in production remains constrained by a multi-dimensional tradeoff between proof-generation latency, bandwidth consumption, and computational complexity. Existing ZKML frameworks and engineering blogs provide qualitative heuristics, yet practitioners lack systematic, layer-level measurements to guide architecture design under these constraints. This work presents the first systematic, layer-level characterization of CNN component costs in EZKL, a Halo2-based ZKML framework targeting EVM-compatible blockchains. We profile 8 feasible layer types (activations, pooling, normalization, and linear) across two EZKL precision settings (scale 7 and 10), measuring proof-generation time, proof size, circuit complexity, and peak memory in 26 experiments. We reveal critical infrastructure requirements by documenting 10 additional experiments that exceeded hardware limits (Conv2d operations, LayerNorm, and ReLU-based composite CNNs requiring$>125\ \text{GB}$RAM). Contrary to conventional wisdom, we find that precision configuration has a negligible performance impact ($1.002 \times$ratio), and that system RAM, not GPU VRAM, is the primary bottleneck. We release an open-source profiling toolkit and a public dataset that enable practitioners to query expected costs for their architectures and constraints.

Vid Keršič, Muhamed Turkanović

Abstract As artificial intelligence (AI) systems become increasingly integrated into critical applications, ensuring trust in their outputs has emerged as a central challenge. Verifiable machine learning (ML) is one approach to addressing this challenge, providing guarantees that results are both correct and reproducible. Existing paradigms, however, provide only partial solutions: zero-knowledge ML (ZKML) achieves strong cryptographic assurances but suffers from limited scalability and high resource costs, while optimistic ML (OPML) supports a wider range of models but relies on economic incentives and long dispute periods. In this work, we propose zk-OPML, a novel hybrid framework that integrates optimistic verification with zero-knowledge proofs (ZKPs). The approach decomposes ML inference into operator-level computations, selectively generating ZKPs for isolated ONNX operators, while retaining the scalability of the optimistic paradigm. We present a prototype implementation and evaluate its performance by benchmarking it against ZKML and OPML. Our results show that zk-OPML achieves faster verification for more complex inference tasks and scales more effectively to larger models, while avoiding the excessive costs of end-to-end ZKML. The modular design of zk-OPML further enables future extensions with the latest advances in the field of ZK.

Menyhért Pálinkó

Abstract We propose federated quantum randomness with client-side sanity (FQR-CSS), a federated architecture that supplies continuously verifiable quantum entropy to cloud hardware security modules (HSMs) and key management services (KMS). In FQR-CSS, each quantum random number generator (QRNG) node emits a randomness contribution along with a post-quantum zero-knowledge proof (ZKP) attesting to device-level operational predicates. An aggregation layer verifies these proofs, runs Byzantine fault tolerance (BFT) consensus (instantiated via HotStuff) over accepted contributions, and publishes a mixed output with an integrity token. We introduce the security notion of verifiable quantum randomness (VQR), comprising unpredictability, quantum-origin guarantee, and federated integrity. We prove VQR under concrete post-quantum cryptographic assumptions. Our proofs utilize Track-A constructions (ZKPs over classical measurement logs), which are fully implementable today. We further outline a theoretical roadmap for Track-B (direct quantum state verification) to guide future research directions. Our empirical evaluation of a post-quantum zk-STARK (Track-A) demonstrates prover latencies of approximately 26 ms for synthetic statistical predicates (K=1024), with sub-millisecond verification times, proof approximately 2.6 KB, and an estimated end-to-end WAN+HotStuff latency approximately 396 ms in our conservative model.

Anthony Coslett

As neural language models are deployed in regulated domains, verifiable model provenance becomes a critical security requirement. We construct an Inference-Time Physical Unclonable Function (IT-PUF) that provides a challenge-response authentication protocol for neural networks, achieving zero false acceptances across 1,012 comparisons spanning 23 models and 16 vendor families. The IT-PUF derives its entropy from a geometrically intrinsic behavioral fingerprint—the delta-gene (the third pre-softmax logit gap)—which we prove is invariant to inference temperature and empirically validate as invariant across six distinct neural architectures. We provide a formal impossibility result for fingerprint spoofing: an interval-splitting theorem proves that no adversarial Kullback-Leibler (KL) budget can simultaneously close the fingerprint gap and avoid detection via accumulated noise. To establish that this security does not degrade at scale, we validate an Equation of State across three independent model families spanning a 147x parameter range (0.5B to 72B). We falsify the assumption of unbounded stiffness but discover a strict positive empirical floor (S_min = 1.1797), from which the Cramér-Rao bound guarantees a computable minimum spoofing cost. The theoretical foundation is formally verified in the Coq proof assistant: 311 theorems across 16 files, with zero uses of "Admitted" and zero vacuous definitions. 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).

Gianpietro Castiglione, Shahriar Ebrahimi, Narges Khakpour

A Software Bill of Materials (SBOM) is a key component for the transparency of software supply chain; it is a structured inventory of the components, dependencies, and associated metadata of a software artifact. However, an SBOM often contain sensitive information that organizations are unwilling to disclose in full to anyone, for two main concerns: technological risks deriving from exposing proprietary dependencies or unpatched vulnerabilities, and business risks, deriving from exposing architectural strategies. Therefore, delivering a plaintext SBOM may result in the disruption of the intellectual property of a company. To address this, we present VeriSBOM, a trustless, selectively disclosed SBOM framework that provides cryptographic verifiability of SBOMs using zero-knowledge proofs. Within VeriSBOM, third parties can validate specific statements about a delivered software. Respectively, VeriSBOM allows independent third parties to verify if a software contains authentic dependencies distributed by official package managers and that the same dependencies satisfy rigorous policy constraints such as the absence of vulnerable dependencies or the adherence with specific licenses models. VeriSBOM leverages a scalable vector commitment scheme together with folding-based proof aggregation to produce succinct zero-knowledge proofs that attest to security and compliance properties while preserving confidentiality. Crucially, the verification process requires no trust in the SBOM publisher beyond the soundness of the underlying primitives, and third parties can independently check proofs against the public cryptographic commitments. We implement VeriSBOM, analyze its security, and evaluate its performance on real-world package registries. The results show that our method enables scalable, privacy-preserving, and verifiable SBOM sharing and validation.

Nicolai Maisch, Shengjian Chen, Alexander Robertus, Samed Ajdinović · 7 authors

This work presents a concept and implementation for the secure storage and transfer of quality-relevant data of milled workpieces from online-quality assurance processes enabled by real-time simulation models. It utilises Non-Fungible Tokens (NFT) to securely and interoperably store quality data in the form of an Asset Administration Shell (AAS) on a public Ethereum blockchain. Minted by a custom smart contract, the NFTs reference the metadata saved in the Interplanetary File System (IPFS), allowing new data from additional processing steps to be added in a flexible yet secure manner. The concept enables automated traceability throughout the value chain, minimising the need for time-consuming and costly repetitive manual quality checks.

Thomas Perry

v2: Corrected affiliation domain to pastoral.tech. This paper presents a unified framework for anticipatory cyber defense integrating eight convergent dimensions: adversarial machine learning countermeasures, supply chain and hardware implant analysis, quantum threat transition analysis, attribution resistance with deepfake forensics, autonomous defense game theory, zero-knowledge proof systems for operational security, temporal correlation at scale, and biological-physical security integration. We formalize the Mantis autonomous defense environment as a Gymnasium-compatible reinforcement learning system with self-play training, introduce Chameleon, a five-channel defensive steganography framework using dynamic key rotation and Shamir Secret Sharing, and develop a ZK-Evidence Ledger for cryptographic evidence chains with Merkle tree notarization and Circom-based inclusion proofs. The convergence of these systems produces an anticipatory architecture where offensive research (Helix synthetic organization detection), defensive operations (Mantis game-theoretic simulation), and attribution resistance (zero-knowledge Merkle proofs) form a closed operational loop.

Usman Khalil, Mueen Uddin, Maha Abdelhaq, Homam ElTaj · 7 authors

This research presents the design and implementation of the Decentralized Smart City of Things (DSCoT), a novel framework leveraging Web3 architecture to enhance the security and authentication of assets in cyber-physical systems (CPSs) for smart cities on a private blockchain. Unlike traditional non-fungible tokens that primarily identify and distinguish financial assets, existing approaches lack robust mechanisms for attributing and authenticating CPS assets such as owners, users, and IoT-enabled smart devices. DSCoT addresses this gap by introducing an extended ERC721 protocol, enabling IoT-enabled devices to have unique blockchain identities similar to user accounts, which enhances device management and tracking. Novel smart contract modules facilitate secure identification and authentication of CPS assets. Evaluated results on a private Hyperledger Besu blockchain show that DSCoT achieves significant performance improvements, including sub-second latency (∼0.1–0.5 s for application programming interface (API) calls), minimal transaction costs (∼0.01–0.05 USD), and a high processing capacity (∼1000 transactions per second (TPS)). These results, along with improved security through immutable authentication records, demonstrate DSCoT’s effectiveness as a scalable and secure solution for smart city CPSs.

João Gião, Fernando Luis-Ferreira, Joao Sarraipa, Ricardo Jardim-Gonçalves

Nowadays, with the increased integration of cloud-computing, data integrity continues to be a problem in the current eHealth sector. This security principle is considered fundamental to ensure the accuracy and reliability of data by ensuring protection from unauthorized and illicit tampering. The present work aims to demonstrate the ability for the Distributed Ledger Technology (DLT) to provide trust and confidence in the healthcare infrastructure for patients, healthcare professionals and policy makers. The DLT has the potential to become one of the most reliable solutions for the many challenges facing the healthcare industry for its potential to enable more secure, transparent, and equitable data management. Although much documentation exists about applications in this domain, it is mostly presented in high-level conceptualization, without detailing the actual development or implementation. This document proposes a metadata-based approach to protect healthcare data integrity in compliance with GDPR, ensuring trustworthy data access for end-users, while demonstrating that the solution can be deployed on low-resource hardware with minimal adaptation effort and time constraints.

Rong Fu, Jia Yee Tan, Ziyu Kong, Shuning Zhang · 8 authors

Zero-knowledge circuits enable privacy-preserving and scalable systems but are difficult to implement correctly due to the tight coupling between witness computation and circuit constraints. We present zkCraft, a practical framework that combines deterministic, R1CS-aware localization with proof-bearing search to detect semantic inconsistencies. zkCraft encodes candidate constraint edits into a single Row-Vortex polynomial and replaces repeated solver queries with a Violation IOP that certifies the existence of edits together with a succinct proof. Deterministic LLM-driven mutation templates bias exploration toward edge cases while preserving auditable algebraic verification. Evaluation on real Circom code shows that proof-bearing localization detects diverse under- and over-constrained faults with low false positives and reduces costly solver interaction. Our approach bridges formal verification and automated debugging, offering a scalable path for robust ZK circuit development.