arXiv cs.AI· Guanqi Lyu, Decheng Qiu, Guangyang Zhang, Fei Zhao, Zhaojun Lu, Jiaji He, Yongqiang Lyu·· 2 小时前AI 评分42
ProcReverser:面向处理器漏洞分析的多智能体黑盒微架构逆向工程
ProcReverser: Multi-Agent Black-Box Microarchitectural Reverse Engineering for Processor Vulnerability Analysis
AI 导读
研究者提出 ProcReverser,一个多智能体系统,可在处理器实现细节不可得时自动完成黑盒微架构逆向工程,利用执行反馈改进实验方案与测试程序。
正文 · 原文
Abstract:When processor implementation details are unavailable, black-box microarchitectural reverse engineering helps security researchers identify hardware conditions related to security vulnerabilities. However, this process requires substantial manual effort to design experiments, develop test programs, and analyze results for each processor. We present ProcReverser, a multi-agent system that automates this process. ProcReverser uses execution feedback to improve experimental plans and test programs and identifies microarchitectural properties from measurements. We develop a comprehensive suite of property identification tasks focused on hardware mechanisms relevant to Spectre-class attacks, covering speculative execution, branch prediction, memory dependence, and cache behavior. We evaluate ProcReverser on the XuanTie C910, the gem5 RISC-V O3 CPU model, and the SiFive P550. ProcReverser achieves Pass@1 and Pass@5 scores of 81.3% and 93.8%, respectively, on C910, and 83.0% and 100.0% on gem5 O3. On the SiFive P550, ProcReverser further characterizes microarchitectural properties covered by the proposed task suite. These findings highlight the potential of automated microarchitectural reverse engineering to support processor vulnerability analysis and defense evaluation.
| Comments: | Corrected an author affiliation |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.20827 [cs.CR] |
| (or arXiv:2611.20827v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.20827 arXiv-issued DOI via DataCite |
Submission history
From: Guanqi Lyu [view email]
[v1]
Mon, 16 Nov 2026 10:11:17 UTC (515 KB)
[v2]
Tue, 17 Nov 2026 05:50:01 UTC (515 KB)
来源:arXiv cs.AI · arxiv.org