IoT device authentication must resist impersonation and credential theft while respecting the computational constraints of edge devices. Existing frameworks rely on static cryptographic keys that, once extracted, enable full impersonation, whereas RF fingerprinting schemes that bind identity to hardware imperfections transmit and store device templates in plaintext, exposing them to template theft and linkability attacks. ZK-RFAuth is a three-phase authentication framework that integrates Siamese neural network-based RF fingerprinting, Groth16 zero-knowledge proof (ZKP) verification, and proof-of-authority blockchain logging. During registration, a Siamese convolutional network extracts a compact embedding from raw I/Q samples and commits a Poseidon hash of the quantized mean template on-chain. During verification, the prover generates a Groth16 proof demonstrating that the L1 distance between a fresh embedding and the registered template falls below a per-device threshold without revealing either vector. The proof and authentication outcome are recorded on-chain for tamper-evident auditing. Evaluated on the WiSig dataset (28 WiFi transmitters, 224,000 frames), ZK-RFAuth achieves 91.4% closed-set accuracy and 2.25% equal error rate at embedding dimension d = 64, with 88.4% genuine acceptance rate and 70.8% open-set rogue rejection using per-device P95 thresholds. The ZKP circuit requires only 972 rank-1 constraint system (R1CS) constraints over 100× fewer than an equivalent SHA-256 circuit producing 144-byte proofs verifiable in approximately 3 ms.
Open access
2 source records
Wireless Signal Modulation Classification
Physical Unclonable Functions (PUFs) and Hardware Security
Shannon's rate-distortion theory treats source symbols as unstructured labels. When the source is a knowledge base equipped with a logical proof system, a natural fidelity criterion is closure fidelity: a reconstruction is acceptable if it preserves the deductive closure of the original. This paper develops a rate-distortion theory under this criterion. Central to the theory is the irredundant core-a canonical generating set extracted by a fixed-order deletion procedure, from which the full deductive closure can be rederived. We prove that the zero-distortion semantic rate equals a quantity that is strictly below the classical entropy rate whenever the knowledge base contains redundant states. More generally, the full semantic rate-distortion function depends only on the core; redundant states are invisible to both rate and distortion. We derive a semantic source-channel separation theorem showing a semantic leverage phenomenon: under closure fidelity, the required source rate is reduced by an asymptotic leverage factor greater than one, allowing the same knowledge base to be communicated with proportionally fewer channel uses-not by violating Shannon capacity, but because redundant states become free. We also prove a strengthened Fano inequality that exploits core structure. For heterogeneous multi-agent communication, an overlap decomposition gives necessary and sufficient conditions for closure-reliable transmission and identifies a semantic bottleneck in broadcast settings that persists even over noiseless channels. All results are verified on Datalog instances with up to 24,000 base facts.
Semantic communication is a paradigm shift in wireless systems that transmits semantic information, such as intent, context, and meaning, instead of raw data to reduce redundant data. At its core, semantic knowledge bases (SKBs) store and organize the contextual knowledge required for accurate encoding, decoding, and reasoning over semantic information. Recently, large language models (LLMs), pretrained on massive and diverse text corpora, have been integrated into SKBs to generate high-quality semantic embeddings, enable zero-shot retrieval of relevant knowledge, and support complex inference tasks across a wide range of domains. However, since the training corpus of LLM may include outdated, malicious, or privacy-sensitive content, LLM-enabled SKBs should be updated efficiently and verifiably to remove specific data without retraining from scratch. In this article, we first conduct a survey on related works and then propose a model-agnostic proof of unlearning framework for LLM-driven SKBs in semantic communications. Specifically, we track the evolution of the unlearning process by measuring drifts in the LoRA adapter subspace. We then execute successive reverse steps and generate the proof trace that a verifier can compare to provide a quantitative and verifiable unlearning guarantee. Finally, experimental results demonstrate the effectiveness of our proposed framework.
Saviz Changizi, Nasibeh Mohammadzadeh, Mohammad Shojafar
This paper presents a first-of-its-kind modular AI framework for telecom fraud detection, integrating machine learning (ML), large language models (LLMs), and blockchain smart contracts to unify statistical classification, semantic reasoning, and decentralized enforcement. A synthetic dataset of 100 users across 300 sessions in Birmingham, UK, simulated telecom usage with$\mathbf{1 \% - 5 \%}$injected fraud, including GPS spoofing, excessive transmission power, and prolonged usage. Seven ML models were trained, with Random Forest optimized using a precision-recall threshold of$\mathbf{0. 7 2 1 7}$. Six configurations varied the decision logic between ML and GPT-4o-based LLMs, with LLMs performing context-aware reasoning via behavioral prompts. Solidity smart contracts on a local Ethereum network enforced decisions, mapping users to blockchain identities with a Proof-of-Stake-style validation mechanism. The ML-only configuration achieved 92.25 % accuracy with perfect user-level precision and recall, while LLM variants enhanced behavioral and temporal reasoning. This framework advances robust and explainable fraud detection for future telecom infrastructures.
Volker Ziegler, Peter Schneider, Harish Viswanathan, Michael Montag · 6 authors
A comprehensive set of security technology enablers will be critically required for communication systems for the 6G era of the 2030s. Trustworthiness must be assured across IoT, heterogenous cloud and networks, devices, sub-networks, and applications. The 6G threat vector will be defined by 6G architectural disaggregation, open interfaces and an environment with multiple stakeholders. Broadly decomposed into domains of cyber-resilience, privacy and trust and their respective intersection, we explore relevant security technology enablers including automated software creation and automated closed-loop security operation, privacy preserving technologies, hardware and cloud embedded anchors of trust, quantum-safe security, jamming protection and physical layer security as well as distributed ledger technologies. Artificial intelligence and machine learning (AI/ML) as a key technology enabler will be pervasive and of pivotal relevance across the security technology stack and architecture. A novel vision for a trustworthy Secure Telecom Operation Map is developed as part of the automated closed loop operations paradigm.
Abstract In recent times, spectrum sensing and spectrum management become a crucial design issue in cognitive radio networks (CRN). To improve the spectrum utilization in CRN, the secondary users (SUs) will try to utilize the spectrum resource when it is unoccupied by the authorized primary users (PUs). At the same time, blockchain principle has been introduced to efficiently identify the legitimate SUs and allocate the spectrum resource as per the demand specified by the SUs. In this view, this article presents a new machine learning (ML) with blockchain‐based spectrum management technique in CRN. The proposed model undergoes three processes, namely spectrum sensing, blockchain‐based spectrum access, and malicious user (MU) identification. Initially, ML‐based extreme learning machine (ELM) technique is applied for spectrum sensing. Then, the presented blockchain approach provides secured spectrum allocation for SUs. Finally, the MUs are identified and to be blocked from accessing the available spectrum resource. An extensive simulation analysis is carried out to ensure the goodness of the proposed model. The obtained results indicated that the proposed model has offered better performance compared with other methods. The experimental outcome stated that under the presence of −20 dB SNR, the proposed method has attained a maximum detection rate of 0.68, whereas the KNN and OR rule methods have demonstrated a minimum detection rate of 0.58 and 0.5, respectively.