Skip to content

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

Oct 12 · Monday

All papers

Found 10 papers
Filter3

Attack type

Jailbreaks6

Attack technique

Gradient and representation optimization32Automated search19Multi-turn escalation6Encoding and obfuscation19Cross-modal payloads57Defense-targeted4Dormant triggers8

Impact

Harmful content6Output manipulation3

System type

Models and APIs9

Attacker access

Black-box6

Attack surface / entry point

User input7Images, audio and video9

Layer

Prompt layer6

System component

MCP and skills9Guardrails and judges22Monitors5Reasoning chains3Permissions and sandboxing3Fine-tuning and open weights8Vision5Image generation3Multimodal10
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Defense-targetedSystem component：MultimodalClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  7. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    提出 Aegis 红队框架，多轮攻击高风险语音 Agent

    arXiv
    2602.07379
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis 红队评测三类语音智能体：查询式访问消掉认证与泄密成功，行为类攻击仍在。

    Aegis 用多轮红队评测已接入业务系统的 ALLM 语音智能体。作者称这是该设定下的 the first systematic red-teaming framework。

    Paper analysisRead analysis
  8. AttacksarXiv 2603.20198

    研究者提出 MM-Plan 多模态越狱框架

    提出 MM-Plan 多模态越狱框架，自动规划多轮图像编辑以越狱视觉独占目标

    arXiv
    2603.20198
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama-3.2-11B, InternVL3-8B, Qwen3-VL-8B and others8
    Abstract作者称全局规划能攻破对单轮攻击更稳的前沿 MLLM。

    MM-Plan 是面向 Visual Exclusivity 的 black-box 多模态红队方法，并配有人工基准 VE-Safety。

    Paper analysisRead analysis
You have reached the end