Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack type

Jailbreaks5Prompt injection5Poisoning and backdoors2

Model risks

Misalignment and value divergence2Dangerous agent actions3Dangerous capabilities0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsModel risks：Misalignment and value divergenceModel risks：Dangerous capabilitiesClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.01091

    Shanghai Jiao Tong University and others propose a trait-direction drift mechanism and probe-space corridor regularization to suppress latent trait transfer in distillation

    提出特征方向漂移机制与探针空间走廊正则，抑制蒸馏潜隐特质迁移

    arXiv
    2609.01091
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-3-12B-IT

    Abstract论文将潜意识学习归结为特征方向漂移的持续累积，并提出走廊正则化在微调中控制隐蔽特征转移。

    Paper analysisRead analysis
You have reached the end