Skip to content

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

Oct 12 · Monday

All papers

Found 41 papers

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.07645

    SkillPoison:用成功经验投毒自进化 Agent 的技能形成

    提出 SkillPoison,用局部有效的成功经验诱导自进化 Agent 形成过度泛化技能

    Published
    Setting
    AI Agent
    Evaluated models
    deepseek-v4-flash, Qwen V3.8 Flash, GPT-5.5
    AbstractSkillPoison 通过局部有效且验证成功的经验诱导技能过度泛化,在多个评测基准上实现了持久的下游攻击影响。

    SkillPoison 提出了一种针对自进化智能体经验到技能形成过程的攻击范式,通过组织已验证的成功经验诱导技能过度泛化。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.04589

    StegoMemory red team testing: agent persistent memory can be used as a cross-session covert channel

    提出 StegoMemory,评测智能体持久记忆作为跨会话隐写信道

    Published
    Setting
    AI Agent
    Evaluated models
    Llama 3.1 405B, Claude 3.5 Sonnet, GPT-4o and others13

    Abstract研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密,写入持久化是主要防御瓶颈,呼吁建立记忆完整性防御。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.38270

    VirusCascade:劫持 LLM 推荐智能体的协同反思机制

    提出 VirusCascade,联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思

    Published
    Evaluated models
    AgentCF, AgentSEQ, AgentRAG and others4
    Abstract作者把反思写回视为推广攻击入口,并用联合操纵和诊断探针研究其持续与传播。

    VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互,试图让目标商品获得更多良性用户曝光。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.35576

    研究提出跨 LLM 助手的记忆跳跃攻击

    提出跨独立 Agent 的记忆跳跃攻击,经共享工件在助手间自传播

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Luna, Kimi-K2.6, GPT-OSS-120B and others6
    Abstract论文证实持久工件与内存可形成跨智能体传播链,揭示了将共享工件纳入安全防线的重要意义。

    该论文系统研究并量化了通过共享持久工件在具有独立私有内存的 LLM 智能体之间发生自传播的“工件介导传播”攻击风险。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入,清空工具 Agent 的思维链以绕过推理监控

    Published
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过,且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.15989

    研究者提出 plan injection 攻击,可绕过思维链监控

    提出 plan injection 攻击,植入良性伪装计划以绕过思维链监视器

    Published
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder-7B-Instruct, Qwen3-8B, DeepSeek-R1-0528 and others6

    Abstract论文指出模型会将外部上下文中的伪装计划改写为自身推理,使思维链监视器失效甚至反向合理化恶意行为。

    Paper analysisRead analysis
  7. AttacksarXiv 2609.13889

    PMPA:针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

    提出 PMPA,经外部源向 Agent 持久记忆投毒并跨会话泄露隐私

    Published
    Evaluated models
    DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max

    Abstract论文提出了持久记忆投毒攻击 PMPA,报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。

    Paper analysisRead analysis
  8. AttacksarXiv 2609.01023

    Akrasia:针对推理型代码 LLM 的隐蔽后门攻击

    提出隐蔽后门攻击 AKRASIA,在推理代码模型提示中植入触发器并伪装思维链

    Published
    Evaluated models
    Claude-Sonnet-5, GPT-5.5, Gemini-3.5-flash and others7

    Abstract论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA,揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。

    Paper analysisRead analysis
  9. AttacksarXiv 2608.05563

    研究者提出 PoisonedEvolution 轨迹投毒攻击

    提出 PoisonedEvolution 轨迹投毒,诱导自演化技能系统固化恶意行为

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, MiniMax-M2.5, DeepSeek-V3.2 and others6
    Abstract论文揭示自演化技能系统的证据晋升漏洞,提出并验证轨迹投毒攻击。

    这篇论文揭示了自演化技能系统在将交互经验转化为持久指令时的安全风险。

    Paper analysisRead analysis
  10. AttacksarXiv 2607.06595

    When Agents Remember Too Much: Memory Poisoning Attacks against Large Language Model Agents

    Proposed GhostWriter memory poisoning, which writes into the agent's long-term memory via email and calendar and activates across sessions

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
    Paper analysisRead analysis