Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 12 papers Another 232 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 ReSA，从对齐模型行为恢复安全奖励并在解码时反转
Published Oct 6
Evaluated models Llama3.1-8B-Instruct , Gemma-7B-Instruct , Qwen2.5-7B-Instruct and others9 Abstract ReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励，并在解码时反转以诱导有害输出。ReSA 是一种对抗攻击：从对齐模型的可观察行为恢复代理安全奖励，再在解码时把该奖励反过来用。 。
提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为
Published Oct 5
Evaluated models DeepSeek-V4-Flash , GPT-4o-mini , GPT-4o and others6 Abstract 良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。 。
提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测
Published Oct 2
Evaluated models Llama2 (7B) , Llama3 (8B) , Qwen2.5 (7B) Abstract 作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。
提出能力洗钱攻击，拆分任务向对齐模型套取能力
Published Sep 14
Evaluated models GPT-5.5 , Claude Opus 4.8 , Grok-4.3 and others7 Abstract 作者提出了能力洗钱攻击，发现未对齐编排器分解咨询对齐模型可恢复能力差距，指出需建立跨会话防御。
提出 OTTER 词元替换越狱，绕过表面毒性审核诱导有害回答
Published Jun 19
Evaluated models gpt-4-turbo , gpt-4o , gpt-4o-mini and others4 Abstract 论文展示了表面毒性与恶意意图的解耦现象，通过标准 API 实现黑盒越狱测试，并提出闭环分类器加固建议。
提出 CFD 跨会话分解攻击，利用工件来源缺口绕过工具型 Agent 的本地检查
Published Jun 8
Evaluated models GPT-4.1 , GPT-5-nano , Claude-3.5-Sonnet and others6 Abstract CFD 用无指令 artifact 把越狱拆到跨会话。CFD 针对工具型 LLM 智能体：利用 artifact 来源不被跟踪这一部署失败模式，把有害目标拆开后延迟组合。
Propose Blindfold, jailbreaking embodied LLMs with action-level manipulation
Published Mar 2
Evaluated models Llama-3.1-8B , DeepSeek-R1-14B , Gemma-3-27B and others8 Abstract Blindfold jailbreaks embodied LLMs with action-level proxy planning, and the authors claim it can bypass semantic checks and is effective in both simulation and real-world settings.Blindfold is a no-box attack against embodied LLM planning modules, rewriting malicious intent into seemingly benign action sequences.
提出纯视觉越狱攻击 VJA，把有害编辑指令编码进图像
Published Feb 11
Evaluated models Nano Banana Pro , GPT Image 1.5 , Qwen-Image-Edit and others9 提出 SpatialJB，用二维版式打散有害输出以绕过输出护栏
Published Jan 14
Evaluated models GPT-4 , DeepSeek-R1 , DeepSeek-V3 and others11 Attacks arXiv 2510.10271 · Oct 12, 2025 提出 MetaBreak，用特殊 token 操纵越狱在线 LLM 服务并绕过审核
Published Oct 12, 2025
Evaluated models Llama-3.3-70B-Instruct , Qwen-2.5-72B-Instruct , Gemma-2-27B-Instruct and others10 Abstract 利用特殊 token 注入对抗平台模板包裹与审核，多场景验证了越狱有效性与互补性。
Attacks arXiv 2510.09023 · Oct 10, 2025 提出自适应攻击框架，击穿越狱与提示注入防御
Published Oct 10, 2025
Evaluated models Gemini-2.5 Pro , GPT-5 Mini , Llama-3.3 70B and others15 Attacks arXiv 2510.02833 · Oct 3, 2025 提出两阶段良性微调攻击，经 FaaS 用良性数据解除安全对齐
Published Oct 3, 2025
Evaluated models Llama2-7b-chat-hf , Llama3-8b-instruct , Deepseek-R1-Distill-Llama3-8b and others10 You have reached the end