Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.25677 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909990655098880 |
|---|---|
| author | Akgul, Hasan Eplik, Mari Rojas, Javier Abdullah, Aina Binti van der Merwe, Pieter |
| author_facet | Akgul, Hasan Eplik, Mari Rojas, Javier Abdullah, Aina Binti van der Merwe, Pieter |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_25677 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ZK-SenseLM: Verifiable Large-Model Wireless Sensing with Selective Abstention and Zero-Knowledge Attestation Akgul, Hasan Eplik, Mari Rojas, Javier Abdullah, Aina Binti van der Merwe, Pieter Cryptography and Security Computation and Language C.2.1; D.4.6; E.3; I.2.6; I.5.4 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. |
| title | ZK-SenseLM: Verifiable Large-Model Wireless Sensing with Selective Abstention and Zero-Knowledge Attestation |
| topic | Cryptography and Security Computation and Language C.2.1; D.4.6; E.3; I.2.6; I.5.4 |
| url | https://arxiv.org/abs/2510.25677 |