Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 10 papers 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。
诊断护栏相对基座在对抗提示上的置信失校
Published Sep 29
Evaluated models Llama-Guard 7B , Llama-Guard-2 8B , Llama-Guard-3 8B and others10 Abstract 对抗包装使 guard 高置信漏检，而对应 base 在同一输入上常更不确定。诊断性分析 ：五个提示词分类 guard 的置信度，在清洁输入上可以较校准，在越狱包装后则变成高置信度的错误判定。
用物理陷阱模型描述 Best-of-N 越狱的攻击面规律
Published Sep 26
Evaluated models Qwen2.5-7B (base) , Llama-3.1-8B-Instruct , Qwen2.5-3B-Instruct and others5 Abstract 四参数势垒模型拟合 BoN 的两预算面，并把指数交叉归因于数据集有限。Biroli 用一个玻璃陷阱式的微观模型，把 Best-of-N 越狱写成熵瓶颈加能量鞍点，并用四个数描述 (N, M) 攻击面及温度依赖。 。
检验混合合规演示教模型的是通用服从还是有害性
Published Jun 19
Evaluated models Llama-3.1-8B-Instruct , OLMo-3.1-32B-Instruct , GPT-OSS-20B and others6 Abstract 良性与有害合规演示不可互换，效应取决于模型、顺序和偏好优化。这项工作问的是：安全对齐模型从混合的良性与有害合规演示中提取的，是通用服从规则，还是请求是否有害。作者控制 Nb、Nh、ϕ 和顺序，检验总量、有害计数与联合计数三个假设，而不是提出新的攻击算法。
解释自回归一致性如何导致浅层安全对齐，并提出随机插入攻击
Published Jun 3 Abstract 作者用自回归一致性串起浅层对齐、插入攻击和最坏延续对齐。作者把浅层安全对齐和一类续写攻击都归到自回归一致性上。
提出多组 IRT 框架拆解跨语言安全护栏退化原因
Published May 17
Evaluated models gpt-4.1-mini , gpt-4o-mini , gpt-4.1-nano and others15 Abstract 多组 IRT 把多语安全失败拆成能力、语言难度和题目特异差距，并在闭源配置上估计这些因子。Zhang、Patel、Truong 与 Koyejo 用多组项目反应理论，解释安全护栏为何随语言变化，而不是只报告一个 JSR。
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 提出 SpinLLM 解释短注入与长注入的越狱缩放交越
Published Mar 12
Evaluated models Llama-3.2-3B-Instruct , Llama-3-8B-Instruct , Llama-3-70B-Instruct and others10 You have reached the end