Skip to content
Conference Open access

SW-PUF: An ML-Resistant Strong PUF Architecture Using Weak-PUF Entropy and Ascon-Hash Obfuscation

Oct 2026 · IEEE/IFIP International Conference on Very Large Scale Integration of System-on-Chip · pp. 1-5 · 0 citations · 11 references

TL;DR

SW-PUF, a weak-PUF-seeded controlled strong PUF with lightweight Ascon-Hash obfuscation, exposes a scalable challenge-dependent CRP interface while maintaining constant per-device server storage and improves robustness against unstable weak PUF responses without hardware-intensive on-chip error correction.

Abstract

Physical Unclonable Functions (PUFs) leverage intrinsic manufacturing variations for lightweight authentication in resource-constrained IoT systems. Weak PUFs provide a limited number of challenge-response pairs (CRPs), whereas conventional strong PUFs are often vulnerable to machine learning (ML) modeling attacks and may incur considerable server-side CRP storage. This paper proposes SW-PUF, a weak-PUF-seeded controlled strong PUF with lightweight Ascon-Hash obfuscation. The weak PUF acts as a device-unique physical entropy primitive, and the external challenge is partitioned for entropy extraction and hash-based response generation. By nonlinearly mixing the weak-PUF-derived entropy bits with external challenges, SW-PUF exposes a scalable challenge-dependent CRP interface while maintaining constant per-device server storage. A server-side reliability-aware authentication strategy further improves robustness against unstable weak PUF responses without hardware-intensive on-chip error correction. Evaluation results demonstrate near-ideal PUF quality, strong ML resistance, and robust authentication, achieving 50.00% uniqueness, 49.99% uniformity, 99.97% reliability, a maximum ML prediction accuracy of 50.03%, and an authentication success improvement from 74.52% to 99.93% under low-reliability conditions.

Read PDF

Similar papers

Open access Oct 2026

FedSRAM-PUF: Federated Bit-Error Correction for Reliable SRAM PUF Authentication

This letter presents a federated learning (FL)-based framework for improving SRAM PUF reliability through distributed bit-error correction, which reduces average BER by 46.49% in the clean setting and by 36.19% under emulated noise-induced drift, while improving response stability for downstream authentication.

Chandranshu Gupta, Meghna Kapoor, Gaurav Varshney · 0 citations
Open access Oct 2026

Investigating the Impact of Low-Rate Error-Correction Codes on Device-Cloning and Reverse-Engineering Attacks on Physical Unclonable Functions

Securing Internet of Things (IoT) devices is important due to the rapid growth of smart devices and increasing demand for artificial intelligence (AI)-enabled functionality. However, IoT devices are often resource-constrained, making robust security measures challenging to implement. To address this issue, physical unc...

Sinan Yavuz, Edwin Naroska, Kai Daniel et al. · 0 citations
Oct 2026

Side Channel Resistant Novel Multi Mode Memory PUF Design for Key Generation and Dual Authentication for IoT

The paper presents support for multiple security functions; the architecture incorporates a mode-selection mechanism that enables two distinct operating configurations within the same hardware platform. In the Weak Mode (W-mode), fixed control patterns are applied, and the Linear Feedback Shift Register (LFSR) is bypas...

B. Narayanapuram, J. Panda · 0 citations
Open access Nov 2026

Deep-learning side-channel analysis of embedded ML-KEM: Single-trace message recovery, cross-device generalization, and frequency-band leakage characterization

This study evaluates ML-KEM on an ARM Cortex-M4 microcontroller under deep learning(DL)-based side-channel attacks (DL-SCA), revealing that a single power trace enables 32-byte message recovery with 99.98% accuracy, while cross-device testing across three chips achieves over 99% accuracy, highlighting critical DL-drive...

Chung-Wei Kuo, Yu-I Hung, Kai-Lun Lin · 0 citations
Open access Oct 2026

A SRAM-PUF-Based ECDSA Authentication Framework for Secure Embedded and IoT Systems

This paper proposes a real-time secure authentication framework based on an SRAM-based Physical Unclonable Function (SRAM-PUF) integrated with the Elliptic Curve Digital Signature Algorithm (ECDSA). Instead of storing secret keys, the proposed approach dynamically regenerates device-unique cryptographic keys from the i...

P. G., G. Sirisha, M. C. Prabavathi et al. · 0 citations
Sep 2026

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

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 watermar...

Ning Lyu, Yun-Tao Liu, Yong-Hong Bai et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.