Skip to content

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

Oct 12 · Monday

All papers

Found 19 papers
Filter4

Attack type

Jailbreaks19Prompt injection12Poisoning and backdoors9Model tampering8Detection evasion11Malicious use0

Attack technique

Gradient and representation optimization19Automated search10Encoding and obfuscation6Role-play and persuasion3Cross-modal payloads4Defense-targeted17

Impact

Harmful content8Output manipulation10

System type

Models and APIs16

Attacker access

Gray-box3White-box7

Attack surface / entry point

User input4Images, audio and video8Weights and gradients8

Layer

Prompt layer8Model layer8Application layer3

System component

Vision5Multimodal6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack type：Model tamperingAttack type：Detection evasionAttack type：Malicious useAttack technique：Gradient and representation optimizationClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    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

    arXiv
    2610.05894
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    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。

    Paper analysisRead analysis
  3. 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

    arXiv
    2610.03166
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    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
  4. AttacksarXiv 2610.01062

    Kernelized Activation Steering：将激活引导推广到再生核希尔伯特空间的新框架

    提出核化激活引导 KAS，在推理时自适应转向激活以诱导越狱

    arXiv
    2610.01062
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Gemma-2-9B-IT, Llama-3.1-8B-Instruct and others4
    AbstractKAS 用核梯度做局部自适应转向，并在线性核下恢复 DiM。

    Kernelized Activation Steering（KAS） 把推理时的激活转向写成核空间中的优化，使更新随当前激活相对源、目标参考集的位置而变化。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.39788

    研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

    提出只训练或篡改多智能体潜在通信链路来提高有害遵从

    arXiv
    2609.39788
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
    Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。

    学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。

    Paper analysisRead analysis
  6. InterpretabilityarXiv 2609.24801

    研究用 XAI 归因分析 Prompt Guard 2，同义词替换可翻转其提示注入判定

    用词级归因指导同义词替换，翻转提示注入检测并验证越狱

    arXiv
    2609.24801
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Prompt Guard 2 (86M), Llama 3.1 8B

    Abstract作者称检测靠分散的词法线索。

    Paper analysisRead analysis
  7. 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

    arXiv
    2608.07430
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    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
  9. Evaluation and benchmarksarXiv 2607.19855

    研究者提出最小范数攻击集成，用鲁棒性曲线替代单一 ε 评测

    提出最小范数攻击集成，用鲁棒性曲线评测图像分类器

    arXiv
    2607.19855
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    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。

    Paper analysisRead analysis
  10. 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

    arXiv
    2605.21541
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    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
  11. AttacksarXiv 2605.08513

    Apple 研究者发现抑制单个神经元即可绕过 LLM 安全对齐

    提出单神经元激活干预，抑制拒答神经元或放大概念神经元以绕过安全对齐

    arXiv
    2605.08513
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others11

    Abstract作者称大模型安全由拒答门控与概念底座构成，干预单个神经元足以双向击穿对齐，且拒答神经元在预训练阶段已然存在。

    Paper analysisRead analysis
  12. 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.

    arXiv
    2604.03117
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    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
  14. 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

    arXiv
    2602.09431
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    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
  17. AttacksarXiv 2601.21531

    Adversarial robustness of large vision-language models under visual token compression

    提出 CAGE 攻击，在视觉 token 压缩下用图像扰动使预测偏离

    arXiv
    2601.21531
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    LLaVA, Qwen2.5-VL, InternVL3-8B and others5
    AbstractCAGE 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。

    Paper analysisRead analysis
  19. AttacksarXiv 2505.23266

    AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体

    提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知

    arXiv
    2505.23266
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    White-box
    Evaluated models
    Lseg, Clip, ViT-L/16 and others5
    AbstractAdvOF 以多视角融合生成对抗物体。

    AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。

    Paper analysisRead analysis
You have reached the end