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.
论证发布时互信息不能认证开源权重抗微调恢复
Published Oct 7
Evaluated models EleutherAI/deep-ignorance-e2e-strong-filter , EleutherAI/deep-ignorance-unfiltered , Google BERT-Tiny and others6 Abstract 作者称零信息仍可一步恢复，表观抗微调可来自参数化。作者研究开源权重模型的篡改抵抗：发布时的互信息是否足以保证微调恢复很慢。
固定有害指令，单轴归因图像到文本越狱的图像属性
Published Oct 4
Evaluated models GPT-4o , Claude Sonnet 4.5 , Qwen3-VL-8B-Instruct and others6 Abstract 固定文本的图像越狱拆解，只在 Qwen 上给出一条有界相关性归因。
遮挡审计 AdvWave-P 音频越狱的频带必要性与解码层关联
Published Oct 4
Evaluated models Qwen2-Audio-7B-Instruct , LLaMA-Omni Abstract AdvWave-P 的八频带排序与能量相关。这是对加性音频越狱 AdvWave-P 的频率与解码器深度审计，受害模型主要是 Qwen2-Audio-7B-Instruct，不提出新攻击。
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。
比较越狱微调与权重正交化去对齐对有害协助和有用性的影响
Published Apr 3
Evaluated models Qwen3-4B-Instruct-2507 , Llama-3.1-8B-Instruct , Qwen2.5-14B and others6 You have reached the end