Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 25 papers Another 240 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.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
Published Oct 9
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 Abstract Hidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出
Published Oct 7
Evaluated models Qwen3-8B , Qwen3-VL-8B-Instruct , Gemma-4-12B Abstract 论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。
提出 STCA，对驾驶视频 VLM 构造可迁移的时空对抗扰动
Published Oct 6
Evaluated models Video-LLaVA-7B , Qwen2.5-VL-7B , Dolphins 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 IAU-FOA，构造可迁移图像扰动以诱导多模态模型输出目标语义
Published Oct 4
Evaluated models Qwen2.5-VL-7B , Qwen2.5-VL-72B , InternVL3-14B and others17 提出 JIL 对抗后缀，压低长度预测以抬高请求调度优先级
Published Oct 2
Evaluated models Llama-3-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others4 Abstract JIL 用对抗后缀压低长度预测，在预测式 LLM 调度中提高自身优先级。JIL 是对预测式 LLM 调度的攻击：用对抗后缀压低长度预测，使请求在 SRPT 式队列里更早得到服务。
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。
用通用扰动对恶意软件分类器及漂移检测器做规避与后门投毒
Published Aug 4
Evaluated models MLP 100-100 , CADE (CAE 512-384-256-128) , CADE (CAE 512-128-32-8) and others6 提出最小范数攻击集成，用鲁棒性曲线评测图像分类器
Published Jul 22
Evaluated models C1–C20（CIFAR-10，Table 1） , I1–I10（ImageNet，Table 1） Abstract 预算可控的最小范数集成用 AOI 逼近攻击前沿，DOI 给出不依赖单一ε的防御排序。这篇工作把对抗鲁棒评测从单一 ε、固定集成，改成可按查询预算收紧的曲线估计。
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 CodecAttack，在编解码器隐空间构造可穿透有损压缩的对抗音频
Published May 20
Evaluated models Qwen2-Audio-7B-Instruct , Audio Flamingo 3 , Qwen2.5-Omni 提出 CrossMPI，仅用图像扰动实现跨模态提示注入
Published May 15
Evaluated models MiniGPT4-llama2 , MiniGPT4-vicuna , InstructBLIP and others6 提出 AudioHijack，用不可感知对抗音频对语音模型做上下文无关提示注入
Published Apr 16
Evaluated models SpeechGPT , GLM-4-Voice , VITA-Audio and others15 Abstract 提出了 AudioHijack 框架，揭示了 LALM 对听觉提示注入的脆弱性与传统防御的局限。
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 CoTTA 隐蔽视觉提示注入，使多模态模型输出指定指令
Published Mar 31
Evaluated models GPT-4o , GPT-5 , Claude-4.5 and others4 Abstract CoTTA 以隐蔽触发和双目标对齐诱导指定句子。
Proposes XSPA, which uses X-shaped sparse adversarial perturbations to transfer attacks on VLMs.
Published Mar 30
Evaluated models OpenCLIP ViT-B/16 , Meta-CLIP ViT-L/14 , EVA-CLIP ViT-G/14 and others10 Proposes MPCAttack, which synergizes multi-paradigm feature optimization for transferable visual adversarial perturbations.
Published Mar 5
Evaluated models Qwen2.5-VL-7B , InternVL3-8B , LLaVa-1.5-7B and others8 提出 TFL 定向比特翻转，使选定提示输出虚假答案且无关查询保持正确
Published Feb 20
Evaluated models Qwen3-8B , DeepSeek-R1-Distill-Qwen-14B , LLaMA-3.1-8B-INSTRUCT Abstract TFL 在三个 LLM 上搜索权重比特，使指定提示出现目标关键词，并约束无关任务下降。TFL 是对 LLM 主存权重的目标比特翻转框架：攻击者要让选定提示输出指定虚假答案关键词，同时限制无关查询上的降质。
Propose GDA, which aligns image adversarial perturbations with text-grounded evidence and transfers attacks to vision-language models
Published Feb 10
Evaluated models LLaVA , Qwen2.5-VL , InternVL3 and others10 Abstract GDA aligns perturbations with text-grounded evidence, and the authors say this improves zero-query black-box transferability on heterogeneous LVLMs.GDA is a zero-query black-box encoder transfer attack for heterogeneous LVLMs.
提出 SGHA-Attack，对视觉语言模型做可迁移定向图像扰动
Published Feb 2
Evaluated models UniDiffuser , BLIP-2 , InstructBLIP and others9 Abstract 用多锚点与分层对齐做定向迁移。SGHA-Attack 是对视觉语言模型的可迁移定向攻击：只在 CLIP 代理上优化扰动，让黑盒模型按指定文本描述图像。要处理的困难是，单一参考加上只对齐代理末层，会使优化绑在该嵌入空间上，中间层语义用不上，异构 VLM 上的指定描述更容易失败。引言把绕过安全护栏列为动机，测的则是描述是否被导向目标文本。