Speculative attacks such as Spectre can leak secret information without being discovered by the operating system. Speculative execution vulnerabilities are finicky and deep in the sense that to exploit them, it requires intensive manual labor and intimate knowledge of the hardware. In this paper, we introduce SpecRL, a framework that utilizes reinforcement learning to find speculative execution leaks in post-silicon (black box) microprocessors.
@article{arxiv.2502.16756,
title = {Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities},
author = {Evan Lai and Wenjie Xiong and Edward Suh and Mohit Tiwari and Mulong Luo},
journal= {arXiv preprint arXiv:2502.16756},
year = {2025}
}