一句话：利用生成式语言模型合成证书，对 TLS 证书验证进行差分测试以发现安全缺陷。
TLS 证书验证是网络安全的关键步骤，差分测试合成证书已能暴露意外接受不可信证书等问题；但随机变异或覆盖率引导的生成方法难以高效产生触发验证差异的输入，且程序与输入建模难以扩展。本文提出用生成式语言模型“幻觉”合成证书，借助模型生成多样化、针对性的证书输入，并在多个 TLS 库上做差分测试，比较验证结果以发现实现间不一致。摘要未给出具体实验数据，但该方法旨在以更低建模成本扩展证书验证测试的输入空间，提升安全缺陷发现能力。
Certificate validation is a crucial step in Transport Layer Security (TLS), the de facto standard network security protocol. Prior research has shown that differentially testing TLS implementations with synthetic certificates can reveal critical security issues, such as accidentally accepting untrusted certificates. Leveraging known techniques, like random input mutations and program coverage guidance, prior work created corpora of synthetic certificates. By testing the certificates with multiple TLS libraries and comparing the validation outcomes, they discovered new bugs. However, they cannot generate the corresponding inputs efficiently, or they require to model the programs and their inputs in ways that scale poorly.
@inproceedings{paperbot11868,
title = {Hallucinating Certificates: Differential Testing of TLS Certificate Validation Using Generative Language Models},
author = {Muhammad Talha Paracha and Kyle Posluns and Kevin Borgolte and Martina Lindorfer and David Choffnes},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773203}
}