Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 13 papers Another 215 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.
提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见
Published Oct 5
Evaluated models LLaDA-8B-Instruct , Dream-v0-Instruct-7B , LLaDA-MoE-7B-A1B-Instruct Abstract 通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。
提出 SN-Guided Diffusion，利用安全神经元实现离线越狱
Published Aug 8
Evaluated models Qwen2.5-7B-Instruct , LLaDA-8B-Instruct , Dream-Instruct-7B and others15 Abstract 论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。
提出 Concept2Scenario，借助内部概念归因发现可迁移的越狱场景
Published Jul 26
Evaluated models Qwen3.5-9B , Llama-3.1-8B , Ministral-3-8B and others6 Abstract 该研究从表征空间因果归因揭示场景削弱拒绝的机制，发现可复用脆弱场景先验，提升多模型黑盒越狱效能与探索速度。
提出 FRA-Attack，用频域对齐与梯度正则做可迁移定向视觉攻击
Published May 20
Evaluated models GPT-5.2 , GPT-5.4 , Claude-Opus-4.6 and others15 Abstract FRA-Attack 以频域对齐和梯度低通做可迁移定向攻击，闭源面板上作者称整体更强，Gemma 除外。FRA-Attack 是面向闭源 MLLM 的迁移式定向图像攻击。作者要解决的是：空间域局部对齐重复全局低频，代理梯度的高频成分又把更新拉向代理自身。
提出 GPO-V，用全局概率优化的视觉扰动越狱扩散视觉语言模型
Published May 8
Evaluated models LLaDA-V , LaViDA Abstract 作者用视觉扰动改 dVLM 的全局生成概率，以绕过两类拒绝。GPO-V 把越狱从“开头必须顺从”改成“整段去噪概率朝肯定方向走”。 。
提出 Misrouter，借 MoE 路由优化仅输入前缀并迁移攻击
Published May 6
Evaluated models GPT-4o mini , Qwen-Plus , Phi-4 and others18 Proposes the universal curved mesh patch UCGP, causing cross-task semantic bias in infrared vision-language models.
Published Apr 3
Evaluated models OpenAI CLIP ViT-L/14 , OpenCLIP ViT-B/16 , Meta-CLIP ViT-L/14 and others10 Abstract UCGP uses one shared curved-grid patch to simultaneously lower the classification and open-ended outputs of IR-VLM.UCGP is a universal physical adversarial patch for infrared vision-language models. The question is: can a patch that can be attached and reused across samples cause stable semantic deviations in the infrared visual evidence shared by classification, description, and VQA. The patch is constrained to a low-frequency curved mesh.
提出 TriageFuzz，用替代模型定位敏感片段做查询高效越狱
Published Mar 24
Evaluated models Gemma-7B-Instruct , Gemma2-9B-Instruct , LLaMA3-8B-Instruct and others9 比较 GCG 对抗 token 作为前缀与后缀的越狱效果
Published Feb 3
Evaluated models deepseek-llm-7b-chat , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others5 提出 UltraBreak，用单张对抗图像对视觉语言模型实施可迁移越狱
Published Feb 1
Evaluated models Qwen2-VL-7B-Instruct , Qwen-VL-Chat , Qwen2.5-VL-7B-Instruct and others13 提出 CAGE 攻击，在视觉 token 压缩下用图像扰动使预测偏离
Published Jan 29
Evaluated models LLaVA , Qwen2.5-VL , InternVL3-8B and others5 Abstract CAGE 对齐压缩瓶颈后，压缩 LVLM 的稳健准确率低于全 token 编码器攻击。CAGE 研究的是：LVLM 在推理时剪枝或合并视觉 token 之后，对抗稳健性该怎么估。
Attacks arXiv 2511.16110 · Nov 20, 2025 提出 MFA 框架，协同突破视觉语言模型的对齐、提示与审核层
Published Nov 20, 2025
Evaluated models MiniGPT-4 , LLaMA-4-Scout-Inst , LLaMA-3.2-11B-Vision-Instruct and others17 Abstract 作者称多层防御的 VLM 仍存在跨模型漏洞，MFA 整合三项技术实现了端到端越狱。
Attacks arXiv 2510.11570 · Oct 14, 2025 提出四种阶段转换攻击，绕过推理模型的安全推理护栏
Published Oct 14, 2025
Evaluated models gpt-oss-20b , gpt-oss-120b , Qwen3-4B-Thinking-2507 and others10 You have reached the end