Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter6

Attack type

Jailbreaks7Prompt injection33Poisoning and backdoors24Model tampering7Detection evasion6

Attack technique

Gradient and representation optimization5Automated search7Multi-turn escalation5Encoding and obfuscation2Defense-targeted6Selection manipulation0

Impact

Harmful content6

System type

Models and APIs3AI Agent3

Attacker access

White-box3

Attack surface / entry point

User input4Weights and gradients3

Layer

Prompt layer54Model layer3Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack technique：Gradient and representation optimizationAttack technique：Encoding and obfuscationAttack technique：Selection manipulationLayer：Model layerLayer：Application layerClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  3. AttacksarXiv 2603.01414

    Jailbreaking embodied LLMs via action-level manipulation

    Propose Blindfold, jailbreaking embodied LLMs with action-level manipulation

    arXiv
    2603.01414
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    No-box (offline transfer)
    Evaluated models
    Llama-3.1-8B, DeepSeek-R1-14B, Gemma-3-27B and others8
    AbstractBlindfold jailbreaks embodied LLMs with action-level proxy planning, and the authors claim it can bypass semantic checks and is effective in both simulation and real-world settings.

    Blindfold is a no-box attack against embodied LLM planning modules, rewriting malicious intent into seemingly benign action sequences.

    Paper analysisRead analysis
You have reached the end