Skip to content

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

Oct 12 · Monday

All papers

Found 19 papers
Filter3

Attack type

Poisoning and backdoors19

Attack technique

Conversation structure manipulation1Defense-targeted8Dormant triggers19

Impact

Harmful content4Unauthorized actions3Output manipulation8

System type

Models and APIs13AI Agent6Embodied systems and robotics4

Attack surface / entry point

User input3Images, audio and video5Training data14Weights and gradients10Distribution channels8

Layer

Prompt layer8Model layer3Application layer37Training and data layer19

System component

Fine-tuning and open weights16Multimodal6
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.
Attack technique：Conversation structure manipulationAttack technique：Dormant triggersLayer：Training and data layerClear all

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

  1. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  2. 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
  3. AttacksarXiv 2610.07723

    Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

    提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答

    arXiv
    2610.07723
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4

    Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.07654

    研究揭示策略蒸馏的安全后门风险

    测量带后门教师经 OPD 向干净学生迁移潜伏后门

    arXiv
    2610.07654
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct
    Abstract作者称 OPD 可在压低无触发词有害率时迁入后门。

    带后门的外部教师经 OPD，可在压低无触发词有害率的同时，把触发条件下的有害行为传给初始干净学生。。

    Paper analysisRead analysis
  5. AttacksarXiv 2610.05793

    研究者训练出按多智能体拓扑触发的代码后门模型

    提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞

    arXiv
    2610.05793
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct

    Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。

    Paper analysisRead analysis
  6. 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
  8. AttacksarXiv 2609.33985

    研究：众包微调数据投毒可放大专有指令抽取

    提出主题锚点投毒，放大众包微调后的专有指令提取

    arXiv
    2609.33985
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4

    Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。

    Paper analysisRead analysis
  9. 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
  10. AttacksarXiv 2609.27422

    RAMP：逆转对抗扰动以增强针对恶意软件检测器的干净标签后门攻击

    提出 RAMP，逆转对抗扰动加强恶意软件检测器的干净标签后门

    arXiv
    2609.27422
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    MalConv, MalConvGCG
    AbstractRAMP 用反转扰动做 clean-label 投毒。

    RAMP 是 score-based black-box 下的 clean-label 后门增强，对象是会微调的 Windows PE 原始字节恶意软件检测器。

    Paper analysisRead analysis
  11. AttacksarXiv 2609.22711

    UBA-ORL：针对离线强化学习的遗忘激活后门攻击

    提出 UBA-ORL，以 BD/CM 样本在遗忘后激活离线 RL 后门

    arXiv
    2609.22711
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    TD3+BC, BCQ, IQL
    AbstractUBA-ORL 用竞争的 BD/CM 样本，使离线 RL 后门在删除伪装轨迹后激活。

    UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门：合法贡献者同时上传共享触发的后门轨迹和伪装轨迹，训练后触发响应被压低，删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法，但能提交可区分批次，并在部署时向观测注入预定触发。

    Paper analysisRead analysis
  12. AttacksarXiv 2609.14060

    AgentQ：针对 LLM Agent 的量化条件后门攻击

    提出量化条件后门 AGENTQ，使智能体仅在量化后触发恶意工具调用

    arXiv
    2609.14060
    Published
    Layer
    Training and data layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-2B, Qwen3.5-4B, Qwen3.5-9B and others6

    Abstract论文研究了智能体量化条件后门风险，提出 AGENTQ 在保持效用的同时实现全精度隐蔽与量化后生效。

    Paper analysisRead analysis
  14. AttacksarXiv 2609.07051

    TrojanWorld：通过想象引导对世界模型智能体植入后门

    提出 TrojanWorld，用物理触发器对世界模型智能体植入想象引导后门

    arXiv
    2609.07051
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    TD-MPC2, DreamerV3, R2-Dreamer

    AbstractTrojanWorld 揭示了世界模型智能体的供应链后门风险，通过在世界模型中操纵想象可实现对闭环动作的持续控制。

    Paper analysisRead analysis
  15. AttacksarXiv 2609.07048

    FreqDoor：面向视觉语言模型的频域后门攻击

    提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门

    arXiv
    2609.07048
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    BLIP-2 (opt-2.7b), InstructBLIP (flan-t5-xl), LLaVA (interleave-qwen)
    AbstractFreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。

    FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。

    Paper analysisRead analysis
  17. 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
  18. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  19. 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