Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Attack technique

Gradient and representation optimization34Automated search48Multi-turn escalation22Encoding and obfuscation43Role-play and persuasion24Conversation structure manipulation9Reasoning-chain manipulation10Cross-modal payloads46Defense-targeted8Dormant triggers2

System type

Models and APIs2coding agent0

Layer

Prompt layer2Model layer3Application layer7Training and data layer16
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack technique：Dormant triggersSystem type：Models and APIsSystem type：coding agentLayer：Prompt layerClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2602.15927

    研究者提出面向多轮对话的视觉记忆注入攻击 VMI

    提出 VMI，用扰动图像在多轮对话中潜伏并仅在触发话题输出预定消息

    arXiv
    2602.15927
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-VL-7B-Instruct, Qwen3-VL-8B-Instruct, LLaVA-OneVision-1.5-8B-Instruct and others5
    AbstractVMI 让扰动图像在多轮 LVLM 中潜伏，作者称触发话题出现后仍可输出预定消息。

    VMI 是面向多轮 LVLM 的定向图像攻击：第三方发布带小扰动的图像，良性用户把它当作普通输入。

    Paper analysisRead analysis
You have reached the end