Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter2

Impact

Harmful content20Unauthorized actions1Data and privacy leaks7Output manipulation32Availability and reliability7

Attack surface / entry point

User input44Web pages and interfaces41Documents and messages40Tool responses69Tool and skill descriptions39Code repositories and dependencies15Retrieval corpus6Memory writes21Inter-agent messages8Images, audio and video9Training data1Weights and gradients4Distribution channels26
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsAttack surface / entry point：Training dataClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
You have reached the end