Skip to content

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

Oct 13 · Tuesday

All papers

Found 232 papers
Filter5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.12292

    The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

    Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations

    Published
    Attacker
    Black-box
    Evaluated models
    LAYA-TD, LAYA-EN, LAYA-ML and others5

    AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.

    Paper analysisRead analysis
  2. DefensesarXiv 2610.11634

    LTBD:用可学习信任边界分隔符防御提示注入

    提出 LTBD,用可学习分隔符隔离可信指令与不可信数据

    Published
    Evaluated models
    Llama3-8B-Instruct, Llama3.1-8B-Instruct, Falcon3-7B-Instruct and others4
    AbstractLTBD 只训练四个分隔符嵌入。

    LTBD 是一种不改基座权重的提示注入防御:只学习用来标出可信指令与不可信数据边界的四个 token 嵌入。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.12524

    An exploration of attacks on AI agent systems

    Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection

    Published
    Setting
    AI Agent
    Evaluated models
    Ollama Mistral 0.9.5, llama3-8b-8192, gemini-2.0-flash-lite and others5
    AbstractSingle-agent filtering and classification can be bypassed by format or wording, and A2A card selection is also biased toward names and descriptions.

    The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.

    Paper analysisRead analysis
  4. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击,但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  5. AttacksarXiv 2610.09264

    研究者提出 PackHallu:经规则文件提示注入对编码 Agent 发起包幻觉攻击

    提出 PackHallu,经规则文件提示注入诱导编码 Agent 换用攻击者指定包

    Published
    Evaluated models
    Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
    AbstractPackHallu 诱导规则文件换包。

    PackHallu 研究一种针对编程智能体规则文件的提示注入:让智能体在本应使用合法依赖时,改导入攻击者指定并控制的包。

    Paper analysisRead analysis
  6. AttacksarXiv 2610.08951

    ASPIRE:面向 LLM Agent 的开放式提示注入红队引擎

    提出 ASPIRE 行为图搜索,开放式发现 Agent 提示注入漏洞

    Published
    Setting
    AI Agent
    Evaluated models
    Gemini-3.7-Flash, DeepSeek-V4-Flash, Gemini-2.5-flash
    AbstractASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。

    ASPIRE 是给搭建方用的智能体提示注入红队引擎,目标是开放式画出可利用的行为路径,而不是在固定任务上打磨一条载荷。

    Paper analysisRead analysis
  7. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER,以确定性检查优先拦截多智能体流水线的内容攻击

    Published
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里,确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  8. 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
  9. AttacksarXiv 2610.07510

    PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.

    提出 PERSISTBD,发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据

    Published
    Evaluated models
    Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
    Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。

    本文研究第三方 LLM 智能体在开发者进行良性监督微调(SFT)和强化学习(RL)后训练时的后门持久性风险。

    Paper analysisRead analysis
  10. DefensesarXiv 2610.07276

    SAFESHIELD:小语言模型部署时安全的决策组织框架

    提出 SAFESHIELD,组织小语言模型部署时的安全决策

    Published
    Evaluated models
    Qwen3-4B-Instruct
    AbstractSAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策,并报告协调依赖影响端到端结果。

    SAFESHIELD 是面向小语言模型的部署时安全框架,把运行时安全从单项审核改写成可检查的决策过程。

    Paper analysisRead analysis
  11. 研究者提出统一滥用监控基准,覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标,统一评测分解攻击和提示注入下的智能体滥用监视

    Published
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架,动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  12. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架,组合良性 Agent 技能诱发恶意行为

    Published
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果,单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合,看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis