ZK-SenseLM: Verifiable Large-Model Wireless Sensing with Selective Abstention and Zero-Knowledge Attestation

2025/10/29 by Akgul, Hasan, Eplik, Mari, Rojas, Javier +2
#C.2.1 #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #D.4.6 #E.3 #FOS: Computer and information sciences #I.2.6 #I.5.4

paper · doi:10.48550/arxiv.2510.25677

Abstract

ZK-SenseLM is a secure and auditable wireless sensing framework that pairs a large-model encoder for Wi-Fi channel state information (and optionally mmWave radar or RFID) with a policy-grounded decision layer and end-to-end zero-knowledge proofs of inference. The encoder uses masked spectral pretraining with phase-consistency regularization, plus a light cross-modal alignment that ties RF features to compact, human-interpretable policy tokens. To reduce unsafe actions under distribution shift, we add a calibrated selective-abstention head; the chosen risk-coverage operating point is registered and bound into the proof. We implement a four-stage proving pipeline: (C1) feature sanity and commitment, (C2) threshold and version binding, (C3) time-window binding, and (C4) PLONK-style proofs that the quantized network, given the committed window, produced the logged action and confidence. Micro-batched proving amortizes cost across adjacent windows, and a gateway option offloads proofs from low-power devices. The system integrates with differentially private federated learning and on-device personalization without weakening verifiability: model hashes and the registered threshold are part of each public statement. Across activity, presence or intrusion, respiratory proxy, and RF fingerprinting tasks, ZK-SenseLM improves macro-F1 and calibration, yields favorable coverage-risk curves under perturbations, and rejects tamper and replay with compact proofs and fast verification.

Citations

• Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Data
• Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
• Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization
• Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
• FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning
• A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning
• Accelerating End-Cloud Collaborative Inference via Near Bubble-free Pipeline Optimization
• Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks
• zk-IoT: Securing the Internet of Things with Zero-Knowledge Proofs on Blockchain Platforms
• WiOpen: A Robust Wi-Fi-based Open-set Gesture Recognition Framework
• ReSup: Reliable Label Noise Suppression for Facial Expression Recognition
• An Overview on IEEE 802.11bf: WLAN Sensing
• Person-in-WiFi: Fine-grained Person Perception using WiFi
• Adversarial Attacks on Deep-Learning Based Radio Signal Classification
• Wi-Fi CSI based Behavior Recognition: From Signals, Actions to Activities
• FreeSense:Indoor Human Identification with WiFi Signals

Related

• Towards Trustworthy Wi-Fi CSI-based Sensing: Systematic Evaluation of Adversarial Robustness
• Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers
• Scale What Counts, Mask What Matters: Evaluating Foundation Models for Zero-Shot Cross-Domain Wi-Fi Sensing
• Membership Inference Attack and Defense for Wireless Signal Classifiers with Deep Learning
• Smart Channel State Information Pre-processing for Joint Authentication and Secret Key Distillation