针对LLM越狱新方法，采用自适应探针引导，克服了传统对比引导的偏差和手动调参局限，提升鲁棒性与有效性。
arXiv:2605.20286v1 Announce Type: cross Abstract: Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language M…
多轮多模态攻击防不胜防？这篇论文提出预测性防御机制，应对未见过的新型攻击。
arXiv:2605.18988v1 Announce Type: cross Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agen…
最新研究揭示：AI检测器会把基础模型输出误判为人类写作
arXiv:2605.19516v1 Announce Type: cross Abstract: As AI-generated text enters the real-world at scale, institutions increasingly use commercial AI-tex…
不再是优化提示词，而是进化攻击方法本身：一篇提出用进化算法自动合成LLM越狱攻击的论文，攻防研究者必读。
arXiv:2511.12710v2 Announce Type: replace Abstract: Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophist…
临床AI系统在细微扰动和多语言场景下存在诊断崩溃风险，这篇系统性审计揭开了安全漏洞。
arXiv:2605.16993v1 Announce Type: cross Abstract: Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, sta…
揭秘LLM如何生成说服性解释，操纵人类对AI辅助决策的信任，一场新型对抗攻击。
arXiv:2602.04003v3 Announce Type: replace Abstract: Most adversarial threats in artificial intelligence (AI) target the computational behavior of mode…