Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 3 papers
Filter2

Attack type

Jailbreaks3

Impact

Harmful content3

Attacker access

Black-box3White-box4

Attack surface / entry point

User input3

Layer

Prompt layer5Model layer3Application layer3Training and data layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attacker access：Black-boxLayer：Model layerTopic: Defenses and guardrailsClear all
  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. DefensesarXiv 2610.08678

    研究揭示投机解码的安全代价并提出 SecureSD 加固方法

    测量有损投机解码的安全代价，并提出 SecureSD 收紧早期验证

    arXiv
    2610.08678
    Published
    Layer
    Model layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    Qwen3-8B, Qwen3-32B, Llama-3.1-8B-Instruct and others6
    Abstract有损推测解码的早期偏离更快抬高越狱与注入风险。

    作者研究有损推测解码在换取速度时，是否会比效用更快地损害越狱与提示注入防护，并给出按位置校正的 SecureSD。

    Paper analysisRead analysis
  3. AttacksarXiv 2606.11817

    研究：语法约束解码可越狱 LLM 生成恶意代码，并提出 CodeShield 防御

    提出 CodeSpear 越狱，借语法约束解码生成恶意代码，并给出 CodeShield 防御

    arXiv
    2606.11817
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-Coder-7B, Qwen2.5-Coder-32B, Qwen2.5-7B and others10

    Abstract论文发现语法约束解码会破坏自然语言安全对齐，提出 CodeSpear 越狱攻击与基于蜜罐代码对齐的 CodeShield 防御。

    Paper analysisRead analysis
You have reached the end