LLMsafe-Spectre: Efficient Spectre Attack Detection in LLM Environments using An Intelligent HPC events Selection Methodology
ACM Transactions on Design Automation of Electronic Systems · 31.03.2027 · 32 (2) · 1-20
DOI: 10.1145/3821636 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 10.11.2026. Verfasst von Quan Zhou und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The widespread adoption of large language models (LLMs) is transforming computing paradigms while introducing new challenges in hardware security vulnerability detection. Existing hardware performance counter (HPC)-based detectors demonstrate high efficacy for conventional applications (e.g., editing Office files, and playing videos) as well as web-accessible LLMs; however, our novel observation reveals that locally deployed large-scale LLMs exhibit access patterns with striking similarity to Spectre attacks. This similarity causes a dramatic deterioration in attack detection accuracy, plummeting from 99.86% to just 66.16% for DeepSeek-7b. To effectively mitigate detection performance degradation, we propose for the first time, LLMsafe-Spectre, a novel intelligent HPC event selection methodology designed for efficient Spectre attack detection in LLM environments. LLMsafe-Spectre is composed of two phases: (1) AI-assisted clustering of HPC events to efficiently narrow the search space, (2) ANOVA-based statistical analysis of inner-group and inter-group variances to pick out Top-K Spectre attack-LLMs discriminative events under limited registers in processors. This approach uniquely addresses the interference caused by LLM access while maintaining detection robustness. We comprehensively evaluate LLMsafe-Spectre across diverse Spectre variants, hardware architectures, web accessible LLMs and locally deployed large-scale LLMs scaling up from 1.5b to 14b. Experimental results demonstrate that our novel solution achieves superior detection accuracy up to 99.91% on average of scaling LLMs, significantly outperforming state-of-the-art approaches.
Zitieren
APA
Zhou, Q., Wen, R., & Jiao, J. (2027). LLMsafe-Spectre: Efficient Spectre Attack Detection in LLM Environments using An Intelligent HPC events Selection Methodology. ACM Transactions on Design Automation of Electronic Systems, 32(2), 1-20. https://doi.org/10.1145/3821636
Vancouver
Zhou Q, Wen R, Jiao J. LLMsafe-Spectre: Efficient Spectre Attack Detection in LLM Environments using An Intelligent HPC events Selection Methodology. ACM Transactions on Design Automation of Electronic Systems. 2027;32(2):1-20. doi:10.1145/3821636
BibTeX
@article{Zhou2027,
author = {Zhou, Quan and Wen, Ran and Jiao, Jiajia},
title = {LLMsafe-Spectre: Efficient Spectre Attack Detection in LLM Environments using An Intelligent HPC events Selection Methodology},
journal = {ACM Transactions on Design Automation of Electronic Systems},
year = {2027},
volume = {32},
number = {2},
pages = {1--20},
doi = {10.1145/3821636}
}
EUVIMED