Skip to content

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

Oct 13 · Tuesday

All papers

Found 3 papers
Filter5

Attack type

Poisoning and backdoors3

Defense type

Model hardening21Inference-time intervention3Detection and filtering7Permissions and approval0

Impact

Output manipulation3

System type

Models and APIs3coding agent0

Attack surface / entry point

User input21Images, audio and video5Training data3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Defense type：Inference-time interventionDefense type：Permissions and approvalSystem type：Models and APIsSystem type：coding agentAttack surface / entry point：Training dataClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.00786

    MROP：针对 Deep JSCC 后门攻击的掩码区域优化净化方法

    提出 MROP，在发射端推理时纯化输入以抵御训练投毒后门

    arXiv
    2609.00786
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    DeepJSCC, SwinJSCC
    AbstractMROP 不重训练，在发射端纯化补丁后门。

    MROP 是 deep JSCC 无线图像传输上的推理时输入纯化，对象是矩形补丁后门。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.03206

    Understanding and mitigating dataset contamination in large language model steering

    Mitigating steering dataset contamination with Lee-Valiant robust means

    arXiv
    2603.03206
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.2-3B-Instruct, Mistral-7b-Instruct-v0.3, OLMo-2-1124-7B-Instruct
    AbstractData poisoning can alter steering; coordinated injection is strongest.

    The authors study how much behavioral control remains at inference time when contrastive steering's training data is contaminated, and whether the robust mean can catch it.

    Paper analysisRead analysis
You have reached the end