Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 262 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.
提出基于决策前隐藏状态的检测与引导，预测并抑制智能体欺骗
Published Oct 5
Evaluated models Qwen3-14B Abstract 论文展示了智能体自发欺骗可在行为显现前由内部表征预测，并通过激活引导证实了表征的行为可操作性。
提出有守卫最小步激活引导，只在关机语境把继续偏好转向接受关机
Published Sep 24
Evaluated models Qwen3.5-0.8B 提出 ARIA，在冻结权重上用 SAE 做推理时遗忘门控
Published Sep 15
Evaluated models DeepSeek-R1-Distill-Qwen-1.5B , Gemma-3-1B-it 在写入点定位拒答方向，经刚性旋转跨架构迁移并门控放大
Published Sep 4
Evaluated models Falcon-Mamba-7B , Falcon3-Mamba-7B , Llama-3.1-8B and others8 Abstract 拒答方向可经刚性旋转跨架构迁移，但必须在各架构的写入点读取。作者研究拒答表示是否随架构改变，结论是表示共享、读取位置随架构变。
提出 INTENT-AS-A-TOOL，用意图工具概率跟踪并干预智能体失准
Published Aug 28
Evaluated models Gemma-4-31B-IT , Qwen3.5-27B , Qwen3-235B-A22B and others5 Abstract 用意图工具的下一动作概率跟踪推理中的失准承诺，并在其成为首选时插入反思。Zhang 等人研究推理型语言模型在职场邮件沙箱里如何走向智能体失准，并提出用动作偏好而不是事后文本标签来跟踪承诺。问题是：有害执行往往出现在推理已经形成意图之后，但 CoT 监控是事后、粗粒度、依赖外部评审的，也看不到模型倾向调用哪个动作。
提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向
Published Jun 22
Evaluated models LLaMA-3.1-8B , Qwen-2.5-7B , Gemma-2-9B Abstract 白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。
提出推理时防御 ICON，探测注意力过聚焦并转向以纠正 Agent 间接提示注入
Published Feb 24
Evaluated models Qwen-3-8B , Llama-3.1-8B , Mistral-8B and others6 Abstract ICON 在推理时检测过聚焦并转向，以兼顾 IPI 安全与任务效用。ICON 在推理时检测 IPI 的注意力过聚焦并转向，避免以拒答中止智能体轨迹。
提出推理时防御 SafeThink，监视思维链并在低于阈值时注入转向前缀
Published Feb 12
Evaluated models R1-Onevision-7B , OpenVLThinker-7B , VLAA-Thinker-7B and others6 提出推理时框架 STaR，抑制大推理模型推理轨迹中的敏感内容
Published Jan 14
Evaluated models DeepSeekR1-Distill-Llama-8B Abstract STaR 以推理时轨迹调控做 LRM unlearning，作者称在 R-TOFU 上遗忘与隐私指标更好。STaR 在推理阶段约束大推理模型的整段 CoT，使指定 forget set 中的敏感内容不出现在中间步骤或最终答案里，且不更新参数。问题来自 LRM 会把敏感知识写进多步推理，而答案级遗忘在 ZeroThink、LessThink 等解码下仍可能泄漏。STaR 先判断查询是否相关并检索遗忘片段，再加安全前缀。
You have reached the end