Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 29 papers

Another 233papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.03166

    LiBRA:通过双向隐空间优化实现检测感知的图像水印去除

    提出 LiBRA,在潜空间双向优化以规避图像水印双侧检测

    Published
    Attacker
    White-box
    Evaluated models
    Stable Signature, YU1, HiDDeN and others4

    AbstractLiBRA 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。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.02172

    BOSS:以广度优先后缀搜索改进 GCG 越狱优化

    提出广度优先后缀搜索 BOSS,改进 GCG 越狱优化

    Published
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Yi-1.5-9B-Chat, Qwen2-7B-Instruct and others8
    AbstractBOSS 把 GCG 类优化从单条深搜索改为多条短轨迹加源侧诊断。

    BOSS 是插在 GCG 类离散 suffix 优化上的搜索框架:局部梯度更新不变,变的是固定预算花在深度还是广度。

    Paper analysisRead analysis
  3. AttacksarXiv 2608.07430

    研究者提出 SN-Guided Diffusion,利用扩散大模型安全神经元实现离线越狱

    提出 SN-Guided Diffusion,利用安全神经元实现离线越狱

    Published
    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。

    Paper analysisRead analysis
  4. AttacksarXiv 2607.23496

    Concept2Scenario:用 SAE 概念归因发现可迁移的越狱场景

    提出 Concept2Scenario,借助内部概念归因发现可迁移的越狱场景

    Published
    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。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.21541

    研究者提出 FRA-Attack 频域正则化方法,提升对闭源 MLLM 的迁移攻击效果

    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
    Attacker
    Black-box
    Evaluated models
    GPT-5.2, GPT-5.4, Claude-Opus-4.6 and others15
    AbstractFRA-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。

    Paper analysisRead analysis
  6. AttacksarXiv 2605.07399

    研究者提出 GPO-V,用全局概率优化越狱扩散视觉语言模型

    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
    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”。。

    Paper analysisRead analysis
  7. AttacksarXiv 2604.24983

    PEO:直接优化原始提示词嵌入的 LLM 白盒越狱方法

    提出 PEO,直接优化原提示词嵌入实现白盒越狱

    Published
    Attacker
    White-box
    Evaluated models
    Vicuna-7B-v1.3, Llama-2-7B-Chat, Qwen3-4B-Instruct and others4
    AbstractPEO 原位优化提示词嵌入、多轮只重攻失败样本。

    PEO是一种不追加对抗 token 的 white-box 越狱:直接改已有提示词嵌入,并只对未成功样本更换续写目标再优化。

    Paper analysisRead analysis
  8. AttacksarXiv 2604.03117

    Unveiling Physical-World Semantic Vulnerabilities: Universal Adversarial Patches for Infrared Vision-Language Models

    Proposes the universal curved mesh patch UCGP, causing cross-task semantic bias in infrared vision-language models.

    Published
    Attacker
    Gray-box
    Evaluated models
    OpenAI CLIP ViT-L/14, OpenCLIP ViT-B/16, Meta-CLIP ViT-L/14 and others10
    AbstractUCGP 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.

    Paper analysisRead analysis
  9. AttacksarXiv 2603.11132

    WebWeaver: Breaking the topology confidentiality of LLM multi-agent systems via covert context inference

    Propose WebWeaver, which compromises only a single agent and recovers the multi-agent communication topology from conversation context.

    Published
    Evaluated models
    Llama 3.1 8B, Qwen 2.5 7B, Mistral NeMo 12B and others6
    AbstractWebWeaver infers topology from context.

    WebWeaver is an inference attack against the confidentiality of LLM-MAS communication topology: it controls only one arbitrary agent and recovers the full graph from dialogue context, rather than querying agent IDs.

    Paper analysisRead analysis
  10. AttacksarXiv 2602.09431

    Grounding-driven attack: Improving the transferability of encoder-based adversarial attacks to large vision-language models

    Propose GDA, which aligns image adversarial perturbations with text-grounded evidence and transfers attacks to vision-language models

    Published
    Evaluated models
    LLaVA, Qwen2.5-VL, InternVL3 and others10
    AbstractGDA 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.

    Paper analysisRead analysis