Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack technique

Encoding and obfuscation2Reasoning-chain manipulation1Defense-targeted4

Impact

Harmful content42Unauthorized actions9Data and privacy leaks6Output manipulation12Oversight failure3
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.
Attack technique：Encoding and obfuscationAttack technique：Reasoning-chain manipulationImpact：Oversight failureClear all

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

  2. 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
  3. AttacksarXiv 2509.09112

    研究：字符级扰动可破坏 LLM 水印，并提出基于遗传算法的去除攻击

    提出字符级扰动与遗传算法去除 LLM 水印

    arXiv
    2509.09112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    OPT-1.3B, LLaMA-3-8B
    Abstract字符级扰动靠更大攻击范围移除水印。

    这篇工作评估推理时 LLM 水印在黑盒、有限查询下的移除难度，并比较字符级、token 级和句子级编辑。

    Paper analysisRead analysis
You have reached the end