Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter4

Attack type

Poisoning and backdoors8

Attack technique

Dormant triggers6

Impact

Harmful content3Output manipulation3

System type

Models and APIs9AI Agent3coding agent0

Attack surface / entry point

User input32Images, audio and video10Training data50Weights and gradients33Distribution channels9

Layer

Model layer5Application layer21Training and data layer9

System component

Fine-tuning and open weights8Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentAttack surface / entry point：Distribution channelsLayer：Training and data layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.09819

    FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门

    arXiv
    2610.09819
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.05453

    研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私

    提出 PLW，用微调把先前对话敏感触发编码进后续生成图像

    arXiv
    2610.05453
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OmniGen2, BAGEL-7B

    AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.33569

    信息黑洞：3D 点云重建中的后门机制研究

    提出 Information Blackhole 与 AGM，控制点云自编码器后门重建到指定形状

    arXiv
    2609.33569
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    FoldingNet, PointDiffusion
    AbstractAGM 用自适应高斯匹配压制 PCAE 投毒潜码中的源几何，九组设置的 CD-ASD 均下降。

    这篇工作研究点云自编码器的训练时后门：干净输入仍自重建，带触发的输入应重建成攻击者指定形状。分类后门只需把预测推向离散标签。PCAE 把源几何与目标信息编进同一个连续潜空间，残留源几何会把重建拉回源形状。

    Paper analysisRead analysis
  5. OtherarXiv 2609.05241

    10a Labs 测绘无审查开源模型生态：3,471 个原始模型与 8,164 次再分发

    梳理去护栏开源模型的生产、再分发与部署供应链

    arXiv
    2609.05241
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Abstract这是一份去护栏模型供应链调查，作者将再分发层视为持续供给和下游部署的连接点。

    10a Labs 调查的是去护栏模型的公开供应链，而非去护栏技术的效果排行榜。作者关注安全行为被移除后，模型如何继续被复制、转换并接入应用。

    Paper analysisRead analysis
  7. DefensesarXiv 2608.02271

    Z-PEFT: Zero-shot backdoor detection for parameter-efficient fine-tuning based on canonical spectral features

    Propose Z-PEFT, which detects PEFT backdoors in a zero-shot manner using per-head spectral features.

    arXiv
    2608.02271
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Z-PEFT, Llama-2-7B, Llama-2-13B and others6
    Paper analysisRead analysis
  8. AttacksarXiv 2604.00627

    When Safe Models Become Dangerous: Exploiting Potential Vulnerabilities in LLM Merging

    提出 TrojanMerge，在源模型植入仅在合并后生效的潜伏分量

    arXiv
    2604.00627
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama 2 M1 (safety-aligned chat variant), Tulu-2-7b, Llama 3 M1 (safety-aligned chat variant) and others9
    Paper analysisRead analysis
You have reached the end