Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 240 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.
测量 LLM 版本更替对科学摘要 AI 改写检测器的影响
Published Oct 8
Evaluated models RoBERTa-base , Pangram Abstract 作者称检测器的基准准确率只是临时的，每次发布都要连同更早版本重验。作者量化的是：科学摘要的 AI 改写筛查，在 LLM 版本不断更换、而人类摘要误标必须少见时，会怎样变。问题来自期刊和会议已经按分数阈值筛查投稿，但基准多停在评估时可得的版本上。
TAPDreamer 用公开编码器做固定补丁。
Published Oct 6
Evaluated models FastWAM , DreamWAM-uncond , DreamWAM-joint and others4 测量系统提示中隐藏日期对评测分数与排名的影响
Published Sep 29
Evaluated models Llama 3.1 Instruct (8B) , Llama 3.1 Instruct (70B) , Gemma 3 Instruct (4B) and others10 Abstract 只改隐藏日期就足以改变分数和排名。这篇工作量化一个评测协议问题：系统提示词里用户看不见、且逐日变化的当前日期，会不会单独改变 LLM 分数。
提出 ENDOPROMPT，以受害者侧伪参考学习降低良性任务效用的前缀
Published Sep 24
Evaluated models Qwen2.5-7B , Llama-3.1-8B , Mistral-7B-v0.3 and others4 Abstract 作者用受害模型续写监督良性效用攻击，并把行为位移、任务退化与请求匹配效果分开评测。ENDOPROMPT 是一种用受害模型自身续写监督前缀生成的 white-box 效用攻击方法。 它针对良性任务失败，不要求产生有害内容或明确拒答。
提出 RolePlay 框架，用人设条件放大 LLM 单次推理开销
Published Jul 29
Evaluated models DeepSeek-V4-Pro , Gemini-3.5-Flash , Qwen-3.5-Plus and others5 提出层级遗传算法 HGA，扰动题目逻辑结构诱发推理模型过度思考
Published May 13
Evaluated models DeepSeek-R1 (671B) , Qwen3-Thinking , GPT-o3 and others5 Abstract HGA 在黑盒推理模型上用逻辑扰动拉长输出，作者称可从小代理迁移，查询成本是其局限。
Proposes DAERT, which uses simulated failures as reward to generate diverse adversarial instructions, exposing VLA language vulnerabilities.
Published Apr 7
Evaluated models π0 , OpenVLA , OpenVLA-7B and others5 Propose SABER, which uses a reinforcement learning attacker to rewrite instructions within a budget to cause VLA task failure.
Published Mar 26
Evaluated models π0-LIBERO , π0.5 , X-VLA and others6 提出 VIDEO STF 评测视频大模型输出重复并压力测试时序扰动
Published Feb 11
Evaluated models LLaVA-Video-7B-Qwen2 , LLaVA-Video-7B-Qwen2-Video-Only , LLaVA-NeXT-Video-7B and others10 Abstract VIDEO STF 把输出重复做成可测、可被时间扰动放大、并可黑盒诱导的失败。VIDEO STF 测量 VideoLLM 的输出重复，并把时间变换用作 black-box 诱导。
You have reached the end