Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter5

Attack type

Jailbreaks1Prompt injection6

Defense type

Model hardening3Inference-time intervention5Detection and filtering4Instruction–data separation1Permissions and approval0Monitoring and auditing10

System component

Monitors0Permissions and sandboxing5Multimodal1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksDefense type：Instruction–data separationDefense type：Permissions and approvalSystem component：MonitorsSystem component：MultimodalClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  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