一篇新论文提出了一个评估AI系统的框架，该框架侧重于行为目标违规，而非传统的资源泄露。它引入了AI渗透的概念，涵盖了诸如提示注入和数据投毒等对抗性路径。另一项研究调查了自主渗透测试，比较了基线编码代理与更复杂的安全工具，并评估了GPT-5.2和GPT-5.5等更新的LLM对性能的影响。 AI
影响 这些论文表明，AI系统的安全评估方法正在发生转变，侧重于行为结果以及LLM在安全任务中的有效性。
排序理由 arXiv上发表的两篇关于AI系统和渗透测试的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2607.13085v1 Announce Type: cross Abstract: Recent autonomous penetration testing papers report high benchmark scores while adding multi-component security harnesses around frontier LLMs. Because these systems often change both architecture and backbone model, it is difficu…
arXiv:2607.14006v1 Announce Type: cross Abstract: Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary f…
Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer suffici…