Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 1 paper
Filter4

Defense type

Model hardening35Inference-time intervention13Detection and filtering15Instruction–data separation1Permissions and approval0Monitoring and auditing8

System type

Models and APIs1coding agent0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Defense type：Instruction–data separationDefense type：Permissions and approvalSystem type：Models and APIsSystem type：coding agentTopic: Defenses and guardrailsClear all
  1. DefensesarXiv 2609.10613

    后验重加权框架解释并缓解多模态大模型上下文越狱

    用后验重加权解释多模态上下文越狱，并提出风险门控的良性示例注入防御

    arXiv
    2609.10613
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others8
    Abstract后验重加权解释上下文越狱的缩放，并支持风险门控的良性示例防御。

    Zhang 等把多模态 ICL 越狱写成对齐模型在安全与有害隐模式之间的推理时后验漂移，并据此做风险门控防御。

    Paper analysisRead analysis
You have reached the end