Skip to content

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

Oct 13 · Tuesday

All papers

Found 4 papers
Filter6

Attack technique

Gradient and representation optimization4Automated search13Multi-turn escalation4Encoding and obfuscation14Role-play and persuasion4Cross-modal payloads10Defense-targeted11Dormant triggers4

Impact

Harmful content3

System type

Models and APIs4coding agent0

Attack surface / entry point

User input3

Layer

Prompt layer4

System component

Memory0Guardrails and judges3Vision18Audio3Video1Multimodal22
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：Gradient and representation optimizationSystem type：Models and APIsSystem type：coding agentSystem component：MemorySystem component：Guardrails and judgesSystem component：VideoClear all

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

  2. InterpretabilityarXiv 2609.24801

    研究用 XAI 归因分析 Prompt Guard 2，同义词替换可翻转其提示注入判定

    用词级归因指导同义词替换，翻转提示注入检测并验证越狱

    arXiv
    2609.24801
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Prompt Guard 2 (86M), Llama 3.1 8B

    Abstract作者称检测靠分散的词法线索。

    Paper analysisRead analysis
  3. AttacksarXiv 2511.16110

    MFA 框架在 17 个视觉语言模型上取得 58.5% 攻击成功率

    提出 MFA 框架，协同突破视觉语言模型的对齐、提示与审核层

    arXiv
    2511.16110
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    MiniGPT-4, LLaMA-4-Scout-Inst, LLaMA-3.2-11B-Vision-Instruct and others17

    Abstract作者称多层防御的 VLM 仍存在跨模型漏洞，MFA 整合三项技术实现了端到端越狱。

    Paper analysisRead analysis
You have reached the end