Hardware-Rooted PUF Fingerprinting for Device-Level Traceability in Knowledge Distillation

Abstract

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.

The authors’ abstract, as arXiv lists it. arXiv’s listings, abstracts included, are free for anyone to reuse.

More in Artificial Intelligence

• arXiv preprint · 25 September 2026

  A Voltage-controlled MTJ-CMOS Neuron Emulating Tunable Izhikevich-Inspired Dynamics

  Kayode Oluwaseyi Adebunmi, Jordan Athas, Allison Fleming and 5 others
• arXiv preprint · 27 September 2026

  MorphAtt: A Neuromorphic Accelerator for Efficient Multi-Head Attention Processing in Spiking Vision Transformers

  Rachmad Vidya Wicaksana Putra, Amirhesam Jafari Rad and Muhammad Shafique
• arXiv preprint · 27 September 2026

  QBX: A Compiler for 2-local Qubit Hamiltonian Simulation on Quantum Chiplets

  Zikun Li, Zhuoming Chen and Zhihao Jia
• arXiv preprint · 24 September 2026

  MagiCFirm: A Runtime for Magic-State Cultivation with Algorithm-Hardware Co-Design

  Jubo Xu, Abbas B. Ziad, Prakash Murali and 1 other
• arXiv preprint · 28 September 2026

  BEHAVE: Functional Behavior Modeling Enables Self-Improving Agents for Hardware Design and Verification

  Yuheng Wu, Berk Gokmen, Sujeeth Jinesh and 5 others

All new papers in Artificial Intelligence