Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack technique

Gradient and representation optimization3Automated search12Multi-turn escalation4Encoding and obfuscation13Role-play and persuasion4Cross-modal payloads8Defense-targeted10

Impact

Harmful content3

System type

Models and APIs3coding agent0Multi-agent systems0

Attack surface / entry point

User input3

Layer

Prompt layer3

System component

Guardrails and judges3Vision17Audio3Multimodal21
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attack technique：Gradient and representation optimizationSystem type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsSystem component：Guardrails and judgesClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. 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