Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

Attack surface / entry point

User input80Web pages and interfaces7Documents and messages10Tool responses12Tool and skill descriptions10Code repositories and dependencies4Retrieval corpus4Memory writes3Inter-agent messages3Images, audio and video19Training data3Distribution channels6

Layer

Training and data layer3

System component

Guardrails and judges3Reasoning chains4Fine-tuning and open weights36Vision7Video3Multimodal13
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Training dataSystem component：Guardrails and judgesClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.07723

    Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

    提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答

    arXiv
    2610.07723
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4

    Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。

    Paper analysisRead analysis
  2. 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