Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917975501570048 |
|---|---|
| author | Lai, Evan Xiong, Wenjie Suh, Edward Tiwari, Mohit Luo, Mulong |
| author_facet | Lai, Evan Xiong, Wenjie Suh, Edward Tiwari, Mohit Luo, Mulong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16756 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities Lai, Evan Xiong, Wenjie Suh, Edward Tiwari, Mohit Luo, Mulong Cryptography and Security Artificial Intelligence 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. |
| title | Towards Reinforcement Learning for Exploration of Speculative Execution Vulnerabilities |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2502.16756 |