Metraipolis › archive › dc_39bb19256008

Hardware-Rooted PUF Fingerprinting for Device-Level Traceability in Knowledge Distillation — arXiv:2609.31968

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.31968
License (as archived): CC0-1.0
Archived: 2026-10-07T22:34:31.208Z
SHA-256 of the archived text: 27e9ca12592b52fc6e21440dbeb409d3e0f43e25b8feec207de011b27bb9e073
Stable URL of this page: https://metraipolis.com/documento/dc_39bb19256008

How to cite

Hardware-Rooted PUF Fingerprinting for Device-Level Traceability in Knowledge Distillation — arXiv:2609.31968 — arXiv (en), https://arxiv.org/abs/2609.31968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_39bb19256008 (Metraipolis archive dc_39bb19256008, sha256 27e9ca12592b52fc6e21440dbeb409d3e0f43e25b8feec207de011b27bb9e073)

BibTeX

@misc{dc39bb19256008,
  title = {Hardware-Rooted PUF Fingerprinting for Device-Level Traceability in Knowledge Distillation — arXiv:2609.31968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_39bb19256008; sha256 27e9ca12592b52fc6e21440dbeb409d3e0f43e25b8feec207de011b27bb9e073},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Knowledge distillation (KD) enables model transfer across heterogeneous platforms and deployment environments, yet it exposes proprietary models to distillation-based theft, where an adversary extracts intellectual property (IP) by training a student model on teacher outputs. Current defenses, such as software watermarking or hardware-based access control, either fail to survive the distillation process or lack the granularity to identify the specific device responsible for a leak. Aiming to provide post-theft accountability and traceability, we propose a novel fingerprinting framework that superimposes device-specific Physical Unclonable Function (PUF) signatures onto teacher logits during distillation. By utilizing signatures derived from Ring Oscillator (RO) PUFs measured on a Xilinx Zynq-7020 FPGA, we ensure that any student model trained via KD inherits a unique, hardware-linked identity. Our framework is architecture-agnostic, enabling reliable identity inheritance across heterogeneous structures, including Convolutional Neural Networks, Vision Transformers, and encoders. To ensure robust attribution, we implement a two-stage recovery pipeline consisting of a neural decoder and Hamming-distance refinement, maintaining high detection accuracy even under noisy conditions. Furthermore, we introduce a multi-level logit encoding scheme to support large-scale device deployment. Experimental results demonstrate that the embedded fingerprints are resilient against common post-distillation modifications. These results establish a practical system-level approach for enabling hardware-linked model traceability in distributed AI deployment environments.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.31968 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:13:03.653Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).