Skip to content

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

Oct 13 · Tuesday

Jailbreaks and attacks · Papers

Found 2 papers
Filter2

Attack technique

Automated search5Multi-turn escalation5Encoding and obfuscation2Defense-targeted5

Layer

Prompt layer32Application layer2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack technique：Encoding and obfuscationLayer：Application layerTopic: Jailbreaks and attacksClear all
  1. 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