← Back ◬ AI & Machine Learning Mar 30, 2026

Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field

arXiv Security Archived Mar 30, 2026 ✓ Full text saved

arXiv:2603.02891v3 Announce Type: replace Abstract: The multi-million dollar investment required for modern machine learning (ML) has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA Cores in a GPU. For the first time, our work demonstrates parameter extraction on the specialized GPU's Tensor Core units, most commonly used GPU units

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Cryptography and Security [Submitted on 3 Mar 2026 (v1), last revised 27 Mar 2026 (this version, v3)] Kraken: Higher-order EM Side-Channel Attacks on DNNs in Near and Far Field Peter Horvath, Ilia Shumailov, Lukasz Chmielewski, Lejla Batina, Yuval Yarom The multi-million dollar investment required for modern machine learning (ML) has made large ML models a prime target for theft. In response, the field of model stealing has emerged. Attacks based on physical side-channel information have shown that DNN model extraction is feasible, even on CUDA Cores in a GPU. For the first time, our work demonstrates parameter extraction on the specialized GPU's Tensor Core units, most commonly used GPU units nowadays due to their superior performance, via near-field physical side-channel attacks. Previous work targeted only the general-purpose CUDA Cores in the GPU, the functional units that have been part of the GPU since its inception. Our method is tailored to the GPU architecture to accurately estimate energy consumption and derive efficient attacks via Correlation Power Analysis (CPA). Furthermore, we provide an exploratory analysis of hyperparameter and weight leakage from LLMs in far field and demonstrate that the GPU's electromagnetic radiation leaks even 100 cm away through a glass obstacle. Comments: To appear at IEEE SaTML 2026 Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2603.02891 [cs.CR] (or arXiv:2603.02891v3 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2603.02891 Focus to learn more Submission history From: Peter Horvath [view email] [v1] Tue, 3 Mar 2026 11:40:13 UTC (29,287 KB) [v2] Tue, 10 Mar 2026 22:45:56 UTC (29,286 KB) [v3] Fri, 27 Mar 2026 15:48:21 UTC (25,525 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev | next > new | recent | 2026-03 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes