研究人员开发了一种名为Tail-risk Intrinsic Geometric Smoothing (TIGS)的新防御机制，用于保护大型语言模型免受后门攻击。TIGS在推理过程中运行，无需模型更新或外部数据，即可识别和破坏恶意注意力模式。另外，一个名为BadStyle的新攻击框架已被提出，它使用自然风格触发器为LLM创建隐蔽的投毒样本。BadStyle旨在通过确保自然性、稳定有效载荷注入以及在现实威胁模型下运行来克服先前攻击的局限性。 AI
影响 新的防御和攻击方法凸显了LLM持续面临的安全挑战，可能影响部署策略和对稳健安全评估的需求。
排序理由 该集群包含两篇学术论文，详细介绍了针对大型语言模型的后门威胁的新攻击和防御方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.24162v1 Announce Type: cross Abstract: Defending against backdoor attacks in large language models remains a critical practical challenge. Existing defenses mitigate these threats but typically incur high preparation costs and degrade utility via offline purification, …
The growing application of large language models (LLMs) in safety-critical domains has raised urgent concerns about their security. Many recent studies have demonstrated the feasibility of backdoor attacks against LLMs. However, existing methods suffer from three key shortcomings…