Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 11 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.
提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱
Published Oct 7
Evaluated models LLaVA-1.5-7B Abstract 剪枝去掉背景 token 后注意力塌向恶意前景。这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。
评测文生图模型的有害内容生成能力与审核检测缺口
Published Oct 5
Evaluated models SDXL , Stable Diffusion 3.5 Large , FLUX.1-dev and others12 提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
Published Sep 30
Evaluated models Stable Diffusion v1.5 , Stable Diffusion XL , Stable Diffusion v3.5 and others4 Abstract NDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
提出 AEGIS，用中层内部信号选择性激活后层适配器拦截音频越狱
Published Sep 24
Evaluated models Qwen2-Audio-7B , VITA-1.5 , Ultravox v0.5 and others6 提出 RAPID，离线把抗蒸馏扰动写入文生图解码器
Published Sep 15
Evaluated models PixArt , SSD , SDXL and others4 提出 SPARK，在预填充阶段修复多模态 KV 记忆以防御视觉语言模型越狱
Published Sep 13
Evaluated models LLaVA-OneVision-7B , Chameleon-7B , Qwen2-VL-7B and others4 提出 EraseSAE，在文生视频模型中局部擦除指定概念
Published Sep 3
Evaluated models CogVideoX-5B , HunyuanVideo , Flux.1 [dev] Abstract EraseSAE 用单义特征局部擦除。EraseSAE 把 SAE 用于 DiT 文生视频模型的概念擦除。作者要解决的是：全局改权重或表面负提示对不齐细粒度、分布式的概念，而且会改到无关时空区域。
提出针对微调 TTS 的黑盒成员推断攻击
Published Sep 2
Evaluated models CosyVoice2 , F5-TTS , XTTS-v2 Abstract 黑盒 TTS 成员推断以 recitation 加分层语音表示为分数，说话人级强于记录级，DP-SGD 可压到随机附近。作者给出一个针对微调文本转语音模型的黑盒成员推断框架，分别审计说话人是否进入微调集，以及某一条文本–音频记录是否进入微调集。微调 TTS 以合成文本和参考语音双条件生成，既有生成模型 MIA 的单条件查询和图像/文本上的逐点比较不能直接套用。作者用 scorable extent 与 memorization elicitation 比较五种查询，认为只有 recitation（用目标转写和干净目标语音要求模型复现）同时满足两条，并把它作为主查询。
提出 SPAR 免训练注意力干预，削弱多模态模型的结构偏置
Published Jul 27
Evaluated models LLaVA-1.5-7B , LLaVA-NeXT Abstract SPAR 以结构偏置净化缓解视觉幻觉，结果需区分误导后收益与原始任务例外。SPAR 是一种无需训练、直接修改多模态内部注意力的幻觉防御。 作者关注视觉信息被查询不变的注意力偏置稀释，以及误导文本进一步推动模型依赖语言先验的问题。
提出 CASG，解决文生图多类别安全引导的方向冲突
Published Feb 24
Evaluated models Stable Diffusion v1.5 , SDv3 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 You have reached the end