Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attacker access

Black-box9Gray-box1

Attack surface / entry point

User input1

System component

Reasoning chains1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attacker access：Gray-boxAttack surface / entry point：User inputSystem component：Reasoning chainsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.15989

    研究者提出 plan injection 攻击，可绕过思维链监控

    提出 plan injection 攻击，植入良性伪装计划以绕过思维链监视器

    arXiv
    2609.15989
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder-7B-Instruct, Qwen3-8B, DeepSeek-R1-0528 and others6

    Abstract论文指出模型会将外部上下文中的伪装计划改写为自身推理，使思维链监视器失效甚至反向合理化恶意行为。

    Paper analysisRead analysis
You have reached the end