Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5

Attack type

Jailbreaks4Model tampering4

Impact

Harmful content3

System type

Models and APIs6coding agent1

Attacker access

Black-box7Gray-box3White-box25

Attack surface / entry point

User input114Code repositories and dependencies2Images, audio and video37Training data4Weights and gradients5Inference services and hardware3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentAttacker access：Black-boxAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Weights and gradientsClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.03124

    研究提出 Untag 攻击框架，使开源大模型触发标签滥用检测机制失效

    提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测

    arXiv
    2610.03124
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Llama2 (7B), Llama3 (8B), Qwen2.5 (7B)
    Abstract作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。

    UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.02293

    SEAL：通过共享专家对齐强化 MoE 全局安全

    提出 SEAL，在 MoE 共享专家上做 DPO-LoRA 对齐以抵御越狱与权重篡改

    arXiv
    2609.02293
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    Qwen1.5-MoE-A2.7B, DeepSeekMoE-16B, GLM-4.7-Flash and others4
    AbstractSEAL 把 DPO-LoRA 限制在混合 MoE 共享专家上，SEAL++再保护已有安全神经元方向。

    SEAL是面向混合 MoE 的训练时防御：只对齐始终执行的共享专家，使安全不依赖路由器是否把 token 送到安全专家。

    Paper analysisRead analysis
  4. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链

    arXiv
    2608.09867
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。

    Paper analysisRead analysis
  5. AttacksarXiv 2608.07430

    研究者提出 SN-Guided Diffusion，利用扩散大模型安全神经元实现离线越狱

    提出 SN-Guided Diffusion，利用安全神经元实现离线越狱

    arXiv
    2608.07430
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen2.5-7B-Instruct, LLaDA-8B-Instruct, Dream-Instruct-7B and others15
    Abstract论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。

    论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。

    Paper analysisRead analysis
  6. AttacksarXiv 2607.11698

    AHA 用自动研究循环发现生产 Agent 漏洞概念

    提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念

    arXiv
    2607.11698
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    Minimax-M2.7, Kimi-K2.6, Deepseek-V4-Pro and others5
    Abstract论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。

    AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。

    Paper analysisRead analysis
  7. AttacksarXiv 2509.22067

    论文：激活引导可破坏 LLM 安全对齐，20 个随机向量即可构造通用越狱攻击

    提出激活转向越狱，用随机向量在推理时绕过安全拒答

    arXiv
    2509.22067
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama3.1-8B, Llama3.1-70B, Qwen2.5-3B and others8

    Abstract作者称激活转向会系统性破坏 LLM 对齐，良性特征与随机向量均能诱发有害合规，聚合随机向量可构建通用攻击。

    Paper analysisRead analysis
You have reached the end