Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter5

Attack type

Poisoning and backdoors8

Defense type

Inference-time intervention3

Impact

Harmful content5Output manipulation8

System type

Models and APIs7

Attack surface / entry point

User input53Web pages and interfaces16Documents and messages27Tool responses17Tool and skill descriptions5Code repositories and dependencies6Retrieval corpus28Memory writes7Inter-agent messages10Images, audio and video43Training data8Weights and gradients6Distribution channels12Inference services and hardware5

Layer

Prompt layer2Model layer5Application layer1Training and data layer24
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Impact：Output manipulationAttack surface / entry point：Training dataLayer：Prompt layerLayer：Model layerLayer：Application layerClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.00348

    NEEDLE：通过权重正交化移除 LLM 后门

    提出 NEEDLE，用权重正交化在已知触发器时去除大模型后门

    arXiv
    2610.00348
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-3-4B-IT, Qwen3-4B-Instruct-2507, Gemma-3-12B-IT

    AbstractNEEDLE 用闭式权重编辑去掉已知触发器的后门，并保住拒绝子空间。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.17817

    论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码

    提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码

    arXiv
    2609.17817
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.5, Qwen3.5-397B, gpt-oss-120b and others5

    Abstract论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。

    Paper analysisRead analysis
  5. 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
  7. DefensesarXiv 2603.03206

    理解并缓解大语言模型引导中的数据集污染

    用 Lee-Valiant 稳健均值缓解 steering 数据集污染

    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
    Abstract数据污染会改 steering，协调注入最强。

    作者研究 contrastive steering 的训练数据被污染后，推理时的行为控制还剩多少，以及稳健均值能否接住。

    Paper analysisRead analysis
  8. DefensesarXiv 2602.03085

    Triggers in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers

    提出推理扫描器，在仅有模型文件时检测后门并重构触发词

    arXiv
    2602.03085
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    gemma-3-270m-it, DeepSeek-R1-Distill-Qwen-1.5B, Phi-4-mini-instruct and others8
    Abstract用记忆泄漏和内部信号重构触发词。

    这是一个只做推理的 sleeper agent 扫描器：在不知触发词和目标行为时，检测因果语言模型里的条件后门并重构触发词。。问题在于，后门只在触发词出现时偏离基线，而开放仓库和网页投毒使检测方通常没有触发词、目标或激活语料。

    Paper analysisRead analysis
You have reached the end