Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter2

Attack surface / entry point

User input12Code repositories and dependencies1Images, audio and video7Training data36Weights and gradients34Distribution channels14

System component

Memory3Guardrails and judges4Reasoning chains3Permissions and sandboxing6Fine-tuning and open weights1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 313papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Code repositories and dependenciesSystem component：Fine-tuning and open weightsClear all

Another 313papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.07510

    PersistBD：攻击者可在发布前强化后门，使其在开发者 SFT 与 RL 后仍保持高攻击成功率

    提出 PERSISTBD，发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据

    arXiv
    2610.07510
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
    Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。

    本文研究第三方 LLM 智能体在开发者进行良性监督微调（SFT）和强化学习（RL）后训练时的后门持久性风险。

    Paper analysisRead analysis
You have reached the end