Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Attack type

Jailbreaks15Prompt injection4Poisoning and backdoors2Model tampering7Detection evasion9

Attack technique

Gradient and representation optimization2Automated search10Encoding and obfuscation4Defense-targeted8Dormant triggers23Selection manipulation3

System type

Models and APIs2LLM applications3coding agent0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Attack type：Poisoning and backdoorsAttack technique：Gradient and representation optimizationSystem type：Models and APIsSystem type：coding agentClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.01367

    研究：高质量数据筛选挡不住投毒

    提出 Bi-QSTO，优化能穿过质量筛选并在微调中削弱安全对齐的投毒样本

    arXiv
    2610.01367
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama2-7B-Chat, Llama3-8B-Instruct, Qwen2-7B-Instruct and others5
    Abstract质量筛选挡不住部分高分样本的安全削弱。

    Bi-QSTO 研究一个实际训练缺口：基于质量的数据选择会先于微调决定样本去留，而以往微调投毒多假设毒样本直接进入训练集。已对齐 LLM 的拒答会被少量有害或看似无害的微调样本削弱。作者用三个问题串起实验：选择能否排除毒样本。

    Paper analysisRead analysis
You have reached the end