Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter5

Attack type

Poisoning and backdoors5

Attack technique

Gradient and representation optimization23Automated search42Multi-turn escalation21Encoding and obfuscation39Role-play and persuasion19Conversation structure manipulation9Reasoning-chain manipulation7Cross-modal payloads32Defense-targeted7Dormant triggers5

Impact

Harmful content5Unauthorized actions5Data and privacy leaks6Output manipulation12

System type

Models and APIs5coding agent0Embodied systems and robotics0

Attack surface / entry point

Training data3Weights and gradients3

Layer

Training and data layer5

System component

Fine-tuning and open weights5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack technique：Dormant triggersImpact：Harmful contentSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. 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
  3. 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
  4. 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