arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.23643cs.CRcs.LG
收藏

更少努力,更短证明:Tamarin中安全协议分析的强化学习

Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin

CISPA Helmholtz Center for Information Security(CISPA 欧洲信息安全中心);Technical University of Munich(慕尼黑技术大学)

Matthias Cosler, Cas Cremers, Bernd Finkbeiner, Mohamed Ghanem, Niklas Medinger

AI总结:

提出一种受AlphaZero和AlphaProof启发的强化学习框架,通过神经启发式引导蒙特卡洛树搜索,在Tamarin中自动生成更短证明,减少人工努力。

摘要:

像Tamarin和ProVerif这样的工具在分析和验证复杂的现实世界协议(如EMV、5G和WPA2)方面取得了显著成功,甚至检测到了零日漏洞。尽管取得了这些成功,验证此类协议仍然是一项耗时、具有挑战性的任务,通常需要大量的人力和专业知识。在本文中,我们提出了一个受AlphaZero和AlphaProof启发的强化学习(RL)框架,该框架为Tamarin实现了一种新的证明搜索风格。我们为Tamarin开发了一个无状态API,充当经典的RL环境。我们通过一个从完成的子证明中学习的神经启发式来指导蒙特卡洛树搜索(MCTS)。我们在16个案例研究上评估了我们的框架,范围从经典协议模型到近期出版物中具有挑战性的最先进协议模型。我们的方法比Tamarin的标准搜索自动找到更多的证明,并且比标准和人工设计的启发式产生更短的证明。我们的流程开箱即用,可帮助Tamarin用户在活跃研究中减少所需的人力。此外,我们的标准化接口为用户提供了一种与Tamarin交互的程序化方式。最后,我们的工作展示了将基于RL的方法适应Tamarin领域的巨大潜力。

英文摘要:

Tools like Tamarin and ProVerif have achieved notable success in analyzing and verifying complex real-world protocols such as EMV, 5G, and WPA2, even detecting zero-day exploits. Despite these successes, verifying such protocols remains a time-consuming, challenging task, often requiring significant human effort and expertise. In this paper, we present a reinforcement learning (RL) framework inspired by AlphaZero and AlphaProof that implements a new style of proof search for Tamarin. We have developed a stateless API for Tamarin that acts as a classical RL environment. We guide a Monte Carlo Tree Search (MCTS) by a neural heuristic that learns from completed subproofs. We evaluate our framework on 16 case studies, ranging from classical protocol models to challenging state-of-the-art protocol models from recent publications. Our method finds more proofs automatically than Tamarin's standard search and produces shorter proofs than both the standard and human-engineered heuristics. Our pipeline is applicable out of the box to assist Tamarin users in active research, reducing the human effort required. Moreover, our standardized interface provides a programmatic way for users to interact with Tamarin. Finally, our work demonstrates the promising potential of adapting RL-based methods to the Tamarin domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑