Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter4

Attack type

Poisoning and backdoors3

Attack technique

Dormant triggers3

Defense type

Model hardening3

System type

Models and APIs6

Attack surface / entry point

Images, audio and video3Training data3

Layer

Prompt layer17Model layer23Application layer14Training and data layer7

System component

Guardrails and judges21Monitors6Reasoning chains16Fine-tuning and open weights50Vision18Audio6Video2Image generation9Embeddings0Multimodal34
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Layer：Training and data layerSystem component：AudioSystem component：VideoSystem component：EmbeddingsClear all

Another 215papers 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
  4. DefensesarXiv 2609.12623

    SteerDuplex：可操控的全双工语音对话模型

    提出 SteerDuplex，用监督微调与两阶段强化学习提升全双工语音对话可控性

    arXiv
    2609.12623
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    SteerDuplex-SFT, SteerDuplex-RL
    AbstractSteerDuplex 用 SFT 提升语音可控，用两阶段 RL 改时序，并记录奖励黑客。

    SteerDuplex 是基于 Moshi 的全双工语音模型，目标是在保留轮替、打断和一般任务能力的同时，按用户指令改变内容与发声。

    Paper analysisRead analysis
  6. DefensesarXiv 2608.18607

    VA-Judger：面向联合视频-音频生成的人类偏好反馈奖励建模

    提出 VA-Judger，用人类偏好训练联合音视频奖励模型

    arXiv
    2608.18607
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    VA-Judger, LTX-2 + VA-Judger
    AbstractVA-Judger 用易到难的人类偏好学习做联合音视频奖励，并用于 LTX-2 后训练。

    VA-Judger 是面向联合音视频生成的思维链全模态奖励模型，用来替代由分维度专家指标拼成的强化学习奖励。

    Paper analysisRead analysis
  7. AttacksarXiv 2606.09499

    研究者提出针对世界模型的机器人学习管线投毒攻击

    提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略

    arXiv
    2606.09499
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    Cosmos-Predict 2.5, Cosmos-Predict 2.5 AC, Dino WM and others4
    Abstract只改视频帧经世界模型投毒。

    只改看似安全的视频帧，经世界模型之后才改变下游机器人策略。 问题在于世界模型进入数据生成后，数据集检查看到的仍是安全演示，合成轨迹却可以变危险。

    Paper analysisRead analysis
You have reached the end