Skip to content

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

Oct 12 · Monday

All papers

Found 12 papers
Filter5

Attack type

Jailbreaks12Prompt injection13Poisoning and backdoors10Model tampering18Extraction and theft7Detection evasion14Malicious use3

Attack technique

Gradient and representation optimization3

Defense type

Inference-time intervention4

Impact

Harmful content11

System type

Models and APIs10

Attacker access

Black-box4White-box5

Attack surface / entry point

User input72Tool responses13Tool and skill descriptions3Images, audio and video7Weights and gradients5

Layer

Prompt layer41Model layer10Application layer2

System component

Vision4Audio3Multimodal7
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：JailbreaksAttack surface / entry point：Images, audio and videoAttack surface / entry point：Weights and gradientsLayer：Model layerLayer：Application layerClear all

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

  1. DefensesarXiv 2610.09703

    研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制

    提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱

    arXiv
    2610.09703
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LLaVA-1.5-7B
    Abstract剪枝去掉背景 token 后注意力塌向恶意前景。

    这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.07125

    PEV 攻击利用嵌入向量加噪越狱六款开源权重模型

    提出 PEV 攻击，在输入嵌入上加高斯噪声越狱开源模型

    arXiv
    2610.07125
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-1.5B-Instruct, Phi-4-mini-3.8B and others6
    AbstractPEV 用 embedding 高斯噪声，在六个模型上越狱 JailbreakBench 全部提示。

    PEV 是对 open-weight LLM 的 embedding 噪声越狱。

    Paper analysisRead analysis
  11. AttacksarXiv 2509.22067

    论文：激活引导可破坏 LLM 安全对齐，20 个随机向量即可构造通用越狱攻击

    提出激活转向越狱，用随机向量在推理时绕过安全拒答

    arXiv
    2509.22067
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama3.1-8B, Llama3.1-70B, Qwen2.5-3B and others8

    Abstract作者称激活转向会系统性破坏 LLM 对齐，良性特征与随机向量均能诱发有害合规，聚合随机向量可构建通用攻击。

    Paper analysisRead analysis
You have reached the end