Skip to content
Oct 13 · Tuesday

Backdoors and poisoning · Papers

Found 1 paper
Filter4

System type

Models and APIs1coding agent0web agent0

System component

Reasoning chains1Fine-tuning and open weights17Multimodal5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：Models and APIsSystem type：coding agentSystem type：web agentSystem component：Reasoning chainsTopic: Backdoors and poisoningClear all
  1. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
You have reached the end