用质量多样性进化算法系统性挖掘LLM安全漏洞，突破传统对抗测试的局限
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not…
自动化红队测试框架，专攻LLM搜索代理的安全漏洞，已被ICML 2026接收。
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date in…
用大语言模型对在线影响力系统进行红队测试，探索攻击极限与防御边界，一篇扎实的AI安全前沿研究。
arXiv:2605.22880v1 Announce Type: cross Abstract: As large language model (LLM)-based agents increasingly participate in online discourse, red-teaming…