Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 233 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 OrthoPurify，用正交投影清除视觉语言模型适配器中的劫持方向
Published Oct 7
Evaluated models LLaVA-1.5-7B , Qwen3-VL-8B , LLaVA-1.5-13B and others5 Abstract 一次投影去掉劫持方向。OrthoPurify 是部署前的 LVLM 后门净化方法，用一次正交投影去掉被劫持的权重更新方向。
提出 LineupRL，用描述到序列识别作可验证奖励训练时序描述模型
Published Oct 1 Abstract LineupRL 用统计近邻上的序列识别做可验证奖励，3B 描述器超过 SFT、两种 RL 奖励和 72B 教师。LineupRL 是给开放式时间序列描述用的 RLVR：不模仿合成参考，而奖励一条描述能否让冻结文本 LLM 从相近序列里认出目标。
用门控 IoU 与 RadGraph 的 GRPO 降低胸片报告幻觉
Published Sep 26
Evaluated models Qwen3-VL-8B-GRPO 提出持续学习下的净化与选择性恢复框架，抵御逐任务训练投毒后门
Published Sep 6
Evaluated models ViT-B/16 Abstract 作者报告任务内净化与恢复可配合动态专家防御后门，但保证依赖分离条件。这是一项面向持续图像分类的后门防御研究 ：模型只使用当前任务数据，同时需要保留过去知识并避免学习恶意监督。
提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器
Published Aug 13
Evaluated models Qwen3.5-9B Abstract SPARED 用防捷径的编辑对抗环训练 9B 推理检测器。SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。
提出无监督对抗微调，加固离散图像 tokenizer
Published Feb 20
Evaluated models UniTok , UniTok-MLLM , TiTok-BL128 and others7 Abstract 无监督嵌入攻击暴露离散 tokenizer 的弱点，只微调 encoder 即可提升多任务鲁棒准确率。作者研究离散图像 tokenizer 的对抗鲁棒性，给出与任务无关的嵌入攻击，以及只微调 encoder 的无监督对抗训练。
Propose SAFT, which uses semantic description ensembles to construct adversarial examples and fine-tune the image encoder
Published Feb 13
Evaluated models ViT-B/32 , CLIP-L/14 Abstract SAFT fine-tunes the CLIP image encoder with ensemble adversarial examples from refined class descriptions to improve the trade-off between zero-shot accuracy and robustness.SAFT is a method for adversarially fine-tuning the CLIP image encoder to improve the accuracy–robustness trade-off in zero-shot classification.
提出 VenomRec 跨模态交互投毒，定向推广多模态推荐物品
Published Feb 6
Evaluated models VIP5 (T5-small) , VIP5 (T5-base) , DiffMM 提出 BackdoorVLM 基准，评测视觉语言模型微调中的后门攻击与防御
Published Nov 24, 2025
Evaluated models LLaVA-1.5-7B , Qwen2.5-VL-7B Abstract BackdoorVLM 统一评测 VLM 后门与防御：含文本触发在低投毒率下更易激活，现有防御跨类型不稳定。BackdoorVLM 是作者提出的 VLM 后门攻击与防御评测基准，作者称它是首个此类综合基准。
You have reached the end