Skip to content

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

Oct 12 · Monday

All papers

Found 15 papers
Filter4

Attack type

Poisoning and backdoors4Model tampering6

Attack technique

Gradient and representation optimization14Automated search4Conversation structure manipulation1Defense-targeted15Dormant triggers22

Impact

Harmful content8Output manipulation6

System type

Models and APIs13

Attacker access

White-box6

Attack surface / entry point

User input3Images, audio and video3Training data4Weights and gradients9

Layer

Prompt layer41Model layer12Application layer21Training and data layer3

System component

Fine-tuning and open weights3
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：Gradient and representation optimizationAttack technique：Conversation structure manipulationLayer：Model layerLayer：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 2610.06083

    研究者提出面向深度强化学习的轨迹级可迁移黑盒对抗攻击

    提出轨迹级可迁移对抗攻击，降低深度强化学习策略的期望回报

    arXiv
    2610.06083
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    DQN, Double DQN (DDQN)
    Abstract轨迹级后退视界攻击在 CartPole 上比逐步 FGSM 类和 Sign 噪声更压低回报。

    这项工作研究 DRL 上的迁移式黑盒观测攻击：受害参数不可访问时，在白盒代理上造扰动再迁移。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见

    arXiv
    2610.05894
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct

    Abstract通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.03166

    LiBRA：通过双向隐空间优化实现检测感知的图像水印去除

    提出 LiBRA，在潜空间双向优化以规避图像水印双侧检测

    arXiv
    2610.03166
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Stable Signature, YU1, HiDDeN and others4

    AbstractLiBRA 用双向潜空间优化规避双侧水印检测，并提高相对反转基线的保真。

    Paper analysisRead analysis
  5. AttacksarXiv 2610.01367

    研究：高质量数据筛选挡不住投毒

    提出 Bi-QSTO，优化能穿过质量筛选并在微调中削弱安全对齐的投毒样本

    arXiv
    2610.01367
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama2-7B-Chat, Llama3-8B-Instruct, Qwen2-7B-Instruct and others5
    Abstract质量筛选挡不住部分高分样本的安全削弱。

    Bi-QSTO 研究一个实际训练缺口：基于质量的数据选择会先于微调决定样本去留，而以往微调投毒多假设毒样本直接进入训练集。已对齐 LLM 的拒答会被少量有害或看似无害的微调样本削弱。作者用三个问题串起实验：选择能否排除毒样本。

    Paper analysisRead analysis
  6. AttacksarXiv 2610.01062

    Kernelized Activation Steering：将激活引导推广到再生核希尔伯特空间的新框架

    提出核化激活引导 KAS，在推理时自适应转向激活以诱导越狱

    arXiv
    2610.01062
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Gemma-2-9B-IT, Llama-3.1-8B-Instruct and others4
    AbstractKAS 用核梯度做局部自适应转向，并在线性核下恢复 DiM。

    Kernelized Activation Steering（KAS） 把推理时的激活转向写成核空间中的优化，使更新随当前激活相对源、目标参考集的位置而变化。

    Paper analysisRead analysis
  8. 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
  9. AttacksarXiv 2605.08513

    Apple 研究者发现抑制单个神经元即可绕过 LLM 安全对齐

    提出单神经元激活干预，抑制拒答神经元或放大概念神经元以绕过安全对齐

    arXiv
    2605.08513
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others11

    Abstract作者称大模型安全由拒答门控与概念底座构成，干预单个神经元足以双向击穿对齐，且拒答神经元在预训练阶段已然存在。

    Paper analysisRead analysis
  11. AttacksarXiv 2602.17837

    TFL: Targeted Bit-Flip Attack against Large Language Models

    提出 TFL 定向比特翻转，使选定提示输出虚假答案且无关查询保持正确

    arXiv
    2602.17837
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, DeepSeek-R1-Distill-Qwen-14B, LLaMA-3.1-8B-INSTRUCT
    AbstractTFL 在三个 LLM 上搜索权重比特，使指定提示出现目标关键词，并约束无关任务下降。

    TFL 是对 LLM 主存权重的目标比特翻转框架：攻击者要让选定提示输出指定虚假答案关键词，同时限制无关查询上的降质。

    Paper analysisRead analysis
You have reached the end