Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 232 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 ReSA，从对齐模型行为恢复安全奖励并在解码时反转
Published Oct 6
Evaluated models Llama3.1-8B-Instruct , Gemma-7B-Instruct , Qwen2.5-7B-Instruct and others9 Abstract ReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励，并在解码时反转以诱导有害输出。ReSA 是一种对抗攻击：从对齐模型的可观察行为恢复代理安全奖励，再在解码时把该奖励反过来用。 。
提出 LiBRA，在潜空间双向优化以规避图像水印双侧检测
Published Oct 2
Evaluated models Stable Signature , YU1 , HiDDeN and others4 Abstract LiBRA 用双向潜空间优化规避双侧水印检测，并提高相对反转基线的保真。
提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测
Published Oct 2
Evaluated models Llama2 (7B) , Llama3 (8B) , Qwen2.5 (7B) Abstract 作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。
复现 Tree-Ring 语义水印的黑盒伪造并恢复检测统计量
Published Sep 11
Evaluated models Stable Diffusion XL base 1.0 提出 Collapse，从端侧混淆暴露视图抽取高效用替代模型
Published Sep 9
Evaluated models BERT-Base , ViT-Base , Qwen2.5-0.5B and others4 Abstract Oprior 是四原语复合的安全边界，Collapse 利用列方向泄漏抽取替代模型，Oext 只被同一攻击评测。这篇工作用代数原语统一若干 TEE 卸载混淆，给出该族的典范边界，再说明该边界挡不住一种分阶段模型抽取。 。
提出黑盒攻击 DRIFT，偏转生成轨迹以去除扩散水印
Published Sep 8 Analyzing the attention head mechanism of continuation-triggered jailbreaks and proposing HCS
Published Mar 9
Evaluated models LLaMA-2-7B-Chat , Qwen2.5-7B-Instruct Abstract The authors state that jailbreaks arise from competition between two types of heads, and that HCS plus distillation can use this competition for inference-time intervention.The authors use attention head mechanism analysis for continuation-triggered jailbreaks: under the same harmful instruction, moving the continuation suffix from after the instruction to outside the prompt boundary makes the model more likely to continue generating along the suffix.
提出 TFA 与 SVA，抑制 ensemble 后门指纹验证
Published Jan 7
Evaluated models LLaMA2-7B , LLaMA3.1-8B-It , Qwen2.5-7B and others11 Abstract 两种 ensemble 攻击 TFA/SVA 抑制后门指纹。TFA 与 SVA 是针对后门式 LLM 指纹的 ensemble 抑制攻击，不改模型参数。所有者用 SFT 写入秘密对，只通过 API 验证版权。攻击者未授权取得模型，不知道触发和指纹，却要把每个模型的验证变成失败，同时让 ensemble 至少不差于性能最高的单模型。
You have reached the end