Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter2

Attack type

Poisoning and backdoors3

System type

Models and APIs3

Attack surface / entry point

Training data3

Layer

Prompt layer28Application layer23Training and data layer4

System component

Guardrails and judges4Fine-tuning and open weights22Image generation3Multimodal7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Layer：Training and data layerSystem component：Guardrails and judgesClear all

Another 261papers 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 2604.03890

    从提示到物理动作：针对 LLM 中介机器人控制系统的结构化后门攻击

    提出结构化 JSON 后门，经投毒 LoRA 在机器人控制中触发恶意动作

    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
  3. AttacksarXiv 2602.01658

    Efficient Adversarial Attacks on High-Dimensional Offline Bandits

    提出三类攻击，训练前扰动奖励模型以劫持离线 bandit

    arXiv
    2602.01658
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Image Reward, Aesthetic Model
    Abstract公开奖励权重可被小扰动劫持离线 bandit，打乱日志只部分缓解。

    作者研究离线 bandit 在奖励模型被事先改权重时，还会不会选出最优臂。

    Paper analysisRead analysis
You have reached the end