Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 261 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.
用 SafeEvo 提取拒绝电路，并提出 SCA 仅微调该电路
Published Oct 7
Evaluated models Llama-3-8B , Qwen-2.5-7B , Mistral-7B-v0.1 and others4 Abstract SafeEvo 识别出基座模型中存在的弱安全电路及其演化动态，据此提出的 SCA 算法实现了安全对齐、能力保留与低过度拒绝的平衡。
提出 TRACE，仅凭检查点更新审计有害合规微调目标
Published Oct 6
Evaluated models Llama-3.1-8B-Instruct , Mistral-7B-Instruct-v0.3 , Qwen3-8B and others6 Abstract 作者称有害合规 SFT 在检查点更新中留下可排序坐标，并据此做只读权重审计。作者在检查点更新里寻找有害合规 SFT 的目标组成，并把读数做成不查询模型、不看未知训练数据的审计分 TRACE。
用因果追踪区分间接提示注入中的角色可读性与有效干预
Published Oct 4
Evaluated models Qwen-2.5-7B , Qwen-2.5-1.5B , Llama-3.1-8B and others8 Abstract 作者称源角色先于强工具选择效应可读，有效编辑还取决于位置、长度和方向来源。在权重固定的白盒模型上，源角色可以先被读出。沿相关方向的编辑是否改变行为，要在目标位点上另测。 。
用配对续写与激活修补分析工具智能体越狱后的安全路由
Published Sep 28
Evaluated models Qwen3-14B , Qwen3.5-9B , Qwen3.5-27B and others8 Abstract 越狱后的同一安全反馈在八个工具智能体上分成三条路由，因果集中在最后几层并可作预测基线。这篇工作把越狱上下文残留之后的运行时安全反馈，做成工具智能体上的三路路由问题，并用激活修补给这个路由一个晚层的因果位点。作者认为，反馈可能恢复合法执行、留下未授权动作，或误伤良性流程，而现有攻击、基准和静态护栏没有在固定历史上把这三种结局分开。配对续写因此从同一冻结检查点分别接中性提醒 N 和安全反馈 S，并交叉保留越狱 J+ 与中和越狱 J0。
提出 TAME，在强化学习中抑制模板激活以缓解思维链混淆
Published Sep 21
Evaluated models Qwen3-VL-8B , Gemma-3-12B-it You have reached the end