Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
Another 213 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.
提出工作流级越狱，让编程 Agent 在开发任务中写入有害示例
Published Jul 5
Evaluated models Claude Sonnet 4.6 , Claude Haiku 4.5 , Gemini 3.1 Pro and others4 Abstract 作者报告 Copilot 后端会在编码工作流中生成其在单轮条件下通常拒绝的有害答案。这是一项生产 IDE 编码智能体的工作流越狱研究 ，受测对象是 Copilot 的四个模型后端，而非评测流水线中的名义目标。
用 abliteration 消融代码 LLM 拒答方向，分离拒答与漏洞注入能力
Published Jun 4
Evaluated models Qwen2.5-Coder-Instruct 3B , Qwen2.5-Coder-Instruct 7B , Qwen2.5-Coder-Instruct 14B Abstract 拒答可用低秩编辑去掉，CWE-89 注入是否成功仍由模型规模决定。这项初步可行性研究用 abliteration 把代码 LLM 的拒答和 CWE 注入能力拆开：意愿可以被低秩编辑解锁，注入是否成功仍看参数规模。
提出 JAWS-Bench，评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性
Published Oct 2, 2025
Evaluated models GPT-4.1 , GPT-o1 , DeepSeek-R1 and others8 Abstract 论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench，发现多文件与智能体推理会明显放大可部署危害。
You have reached the end