Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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.
比较高效与高成本训练的对抗和隐私脆弱性并分析损失几何
Published Sep 28
Evaluated models ResNet-18 , Swin Transformer , Qwen2.5-Math-7B-Instruct and others7 Abstract 效用匹配下，三种高效训练都伴随更高的隐私与对抗脆弱性及更尖的损失几何。作者在视觉分类和数学推理语言模型上，检查用更少数据或更简对齐换取训练效率时，安全性质是否一起变化。比较在任务效用接近的前提下进行。视觉侧用 KNN-Shapley 的高重要性小子集对照低重要性大子集，并用预训练微调对照从头训练。
提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控
Published Sep 23
Evaluated models openai/gpt-oss-20b , google/gemma-4-26B-A4B-it , deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4 Abstract 论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。
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 You have reached the end