LLM-Falsifier 用大语言模型破解物理系统安全漏洞
Large Language Models as Falsifiers for Cyber-Physical Systems
朋友，DeepSeek 团队搞了个新东西，叫 LLM-Falsifier，能帮着找物理系统里的安全漏洞，比以前的方法更高效。
这篇论文提出了一种名为 LLM-Falsifier 的新方法，它将大语言模型（LLM）用于网络安全物理系统（CPS）的漏洞检测。与传统方法相比，LLM-Falsifier 通过最小化信号时序逻辑（STL）的鲁棒度来寻找反例，在 ARCH-COMP 基准测试中，在 14/21 个规格上表现更优，平均所需模拟次数更少。
Large Language Models as Falsifiers for Cyber-Physical Systems
Falsification searches for counterexamples to formal specifications in cyber-physical systems (CPS). With specifications written in Signal Temporal Logic (STL), falsification can be formulated as a robustness optimization problem, traditionally tackled with black-box search algorithms. In parallel, large language models (LLMs) have recently emerged as surprisingly effective optimizers when coupled with iterative prompting. In this work, we connect these ideas and introduce LLM-Falsifier, an LLM-based approach that falsifies specifications by minimizing the STL robustness degree. Beyond generic prompt-based optimization, our key idea is to expose the LLM to semantic information that is natural for language models but absent from standard numerical optimizers, including natural-language input and output names, output trajectories, and critical-time witnesses for the minimum robustness value. These additions enable smarter and more sample-efficient robustness search. On the ARCH-COMP falsification benchmarks, LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.
