Interpreting Emergent Features in Deep Learning-based Side-channel Analysis
Sengim Karayalcin, Marina Krcek, Stjepan Picek
Abstract
Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the same techniques to certify device security. In recent years, deep learning has emerged as a prominent method for SCA, achieving state-ofthe-art attack performance at the cost of interpretability. Understanding how neural networks extract secrets is crucial for security evaluators aiming to defend against such attacks, as only by understanding the attack can one propose better countermeasures. In this work, we apply mechanistic interpretability to neural networks trained for SCA, revealing how models exploit what leakage in side-channel traces. We focus on sudden jumps in performance to reverse engineer learned representations, ultimately recovering secret masks and moving the evaluation process from blackbox to white-box. Our results show that mechanistic interpretability can scale to realistic SCA settings, even when relevant inputs are sparse, model accuracies are low, and side-channel protections prevent standard input interventions.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Towards Automated Circuit Discovery for Mechanistic Interpretability cites Causal Abstractions of Neural Networks
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks cites Towards Automated Circuit Discovery for Mechanistic Interpretability
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks cites The Quantization Model of Neural Scaling
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks cites A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations
Cited by top-tier papers1
Builds on15
- Towards Automated Circuit Discovery for Mechanistic InterpretabilityArthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch, Stefan Heimersheim et al.NeurIPS 2023 · 861 citations
- Causal Abstractions of Neural NetworksAtticus Geiger, Hanson Lu, Thomas Icard, Christopher PottsNeurIPS 2021 · 516 citations
- The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural NetworksZiqian Zhong, Ziming Liu, Max Tegmark, Jacob AndreasNeurIPS 2023 · 181 citations
- The Quantization Model of Neural ScalingEric J. Michaud, Ziming Liu, Uzay Girit, Max TegmarkNeurIPS 2023 · 179 citations
- A Toy Model of Universality: Reverse Engineering how Networks Learn Group OperationsBilal Chughtai, Lawrence Chan, Neel NandaICML 2023 · 144 citations
Related papers
- Learning From A Big Brother - Mimicking Neural Networks in Profiled Side-channel AnalysisDaan van der Valk, Marina Krcek, Stjepan Picek, Shivam BhasinDAC 2020 · 9 citations
- Cross-Device Profiled Side-Channel Attacks using Meta-Transfer LearningHonggang Yu, Haoqi Shan, Maximillian Panoff, Yier JinDAC 2021 · 38 citations
- SoK: Neural Network Extraction Through Physical Side ChannelsPéter Horváth, Dirk Lauret, Zhuoran Liu, Lejla BatinaUSENIX Security 2024 · 11 citations
- On the Success Rate of Side-Channel Attacks on Masked Implementations: Information-Theoretical Bounds and Their Practical UsageAkira Ito, Rei Ueno, Naofumi HommaCCS 2022 · 18 citations
- There's always a bigger fish: a clarifying analysis of a machine-learning-assisted side-channel attackJack Cook, Jules Drean, Jonathan Behrens, Mengjia YanISCA 2022 · 35 citations
