Skip to content

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

Oct 13 · Tuesday

All papers

Found 21 papers

Another 215papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.09941

    OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型

    提出 OrthoPurify,用正交投影清除视觉语言模型适配器中的劫持方向

    Published
    Evaluated models
    LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
    Abstract一次投影去掉劫持方向。

    OrthoPurify 是部署前的 LVLM 后门净化方法,用一次正交投影去掉被劫持的权重更新方向。

    Paper analysisRead analysis
  2. 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

    Published
    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
  3. DefensesarXiv 2609.06346

    面向后门攻击下持续学习的鲁棒动态扩展:净化与选择性恢复

    提出持续学习下的净化与选择性恢复框架,抵御逐任务训练投毒后门

    Published
    Evaluated models
    ViT-B/16
    Abstract作者报告任务内净化与恢复可配合动态专家防御后门,但保证依赖分离条件。

    这是一项面向持续图像分类的后门防御研究:模型只使用当前任务数据,同时需要保留过去知识并避免学习恶意监督。

    Paper analysisRead analysis
  4. 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

    Published
    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
  5. AttacksarXiv 2606.04329

    研究者系统研究 LLM 智能体记忆投毒攻击并提出 MPBench 基准

    系统研究 LLM 智能体记忆投毒并构建基准 MPBench

    Published
    Setting
    AI Agent
    Evaluated models
    Meta-Llama-3.1-70B-Instruct, Deberta-v3-base, Llama-3.1-8B-Instruct and others5

    Abstract系统研究了智能体记忆投毒风险,揭示了写入渠道漏洞,构建了 MPBench 基准并指出提示注入防御的局限。

    Paper analysisRead analysis
  6. AttacksarXiv 2605.15338

    Hidden in Memory: Latent Memory Poisoning of LLM Agents

    提出潜伏记忆投毒,诱导 Agent 把外部文档写成持久伪造记忆

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.5, Claude Sonnet 4.6 and others12
    Abstract持久记忆成为跨会话攻击面:通用载荷可写入伪造记忆,并在相关后续任务中影响行为。

    sleeper memory poisoning 研究带持久记忆的 LLM 助手:外部文档能否让助手存下一则伪造的用户记忆,并在原文档消失后的新会话里被取回、用来改变回复或动作。

    Paper analysisRead analysis
  7. 论文提出 eTAMP 攻击:网页内容注入可跨会话污染 Web Agent 记忆

    提出 eTAMP,用网页内容跨会话投毒 Web Agent 轨迹记忆并诱导越权操作

    Published
    Setting
    web agent
    Evaluated models
    GPT-5-mini, GPT-5.2, GPT-OSS-120B and others6
    Abstract论文提出了基于环境注入的跨任务记忆投毒攻击 eTAMP,作者报告智能体在环境压力下易感性增加且能力与安全并不协同。

    该论文评估了基于大语言模型的 Web 智能体在利用历史交互轨迹进行记忆增强时的安全脆弱性。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.12644

    Revealing security threats and defense architectures for autonomous agents: an OpenClaw case study

    Reviews threats to autonomous agents and proposes a full-lifecycle defense blueprint, FASA

    Published
    Setting
    AI Agent
    AbstractUsing OpenClaw as an example, it divides risks into three layers and uses FASA to describe defense from input to system execution.

    This is a threat review and defense architecture report using OpenClaw as a case study, not a scored attack or defense evaluation.

    Paper analysisRead analysis
  9. DefensesarXiv 2603.11619

    Taming OpenClaw: Security Analysis and Mitigation of Threats in Autonomous LLM Agents

    Proposes a defense-in-depth aligned with the five stages to mitigate cross-stage threats to autonomous agents

    Published
    Setting
    AI Agent
    AbstractThis is a lifecycle threat analysis and layered mitigation design for OpenClaw, with the cases serving as qualitative evidence.

    This is a lifecycle threat analysis of OpenClaw, accompanied by a set of layered mitigation designs. The problem addressed is: when autonomous agents connect instant messaging, persistent memory, third-party plugins, and high-privilege execution, attacks are no longer limited to single-turn jailbreaks but can compound across multiple stages from initialization to execution. The authors argue that defenses hardening only individual interfaces cannot stop such cross-temporal attacks.

    Paper analysisRead analysis
  10. AttacksarXiv 2602.15654

    Zombie Agent: Persistent Control of Self-Evolving LLM Agents via Self-Reinforcing Injection

    提出 Zombie Agent 攻击,经网页间接注入将载荷写入长期记忆并跨会话触发

    Published
    Setting
    AI Agent
    Evaluated models
    Gemini-2.5-Flash, GLM-4.7-Flash
    Abstract记忆写入把一次网页间接注入变成跨会话控制。

    Zombie Agent 把自进化 LLM 智能体的跨会话记忆当成攻击面:攻击者只发布网页,良性任务读入后,正常记忆更新留下载荷,并在以后无关会话里触发未授权工具行为。

    Paper analysisRead analysis