Skip to content

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

Oct 13 · Tuesday

All papers

Found 119 papers
Filter6

Attack type

Prompt injection37Poisoning and backdoors29Detection evasion11

Attack technique

Gradient and representation optimization9Automated search13Encoding and obfuscation8Role-play and persuasion8Conversation structure manipulation3Cross-modal payloads4Dormant triggers7

Model risks

Deception and scheming4Misalignment and value divergence5Dangerous agent actions5Hallucination and fabrication8

Defense type

Model hardening4Inference-time intervention3Detection and filtering13Instruction–data separation5Permissions and approval3Monitoring and auditing4

Impact

Harmful content24Unauthorized actions78Data and privacy leaks38Output manipulation119Availability and reliability28Oversight failure34Increased misuse capability6

System type

Models and APIs173LLM applications74AI Agent104coding agent14science agent6web agent5Browser and computer use2Multi-agent systems26Embodied systems and robotics6

Attacker access

Black-box8

Attack surface / entry point

User input21Web pages and interfaces10Documents and messages20Code repositories and dependencies5Retrieval corpus22Memory writes3Inter-agent messages10Images, audio and video7Training data5Distribution channels4

Layer

Prompt layer8Model layer7Application layer98Training and data layer6

System component

Memory7RAG24Guardrails and judges23Monitors4Reasoning chains3Permissions and sandboxing3Vision10Embeddings5Multimodal13
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.
Impact：Output manipulationSystem type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useSystem type：Multi-agent systemsSystem type：Embodied systems and roboticsClear all

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

  1. OtherarXiv 2610.13810

    Using subsequence association filtering and breadth-aware selection to suppress hallucinated words in LLM query expansion

    Proposes SAFE-QE, which filters unsupported hallucinated words in LLM query expansion

    arXiv
    2610.13810
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    BM25, SPLADE, Contriever

    AbstractSAFE-QE suppresses expansion hallucinations with reproducibility and coverage selection; the authors say ranking quality shows no visible cost.

    Paper analysisRead analysis
  4. AttacksarXiv 2610.11932

    A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

    Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.

    arXiv
    2610.11932
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Grok, Doubao, ChatGPT and others10

    AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.

    Paper analysisRead analysis
  5. 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

    arXiv
    2610.11634
    Published
    Layer
    Application layer
    Setting
    LLM applications
    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
  8. DefensesarXiv 2610.09496

    SOUL：用稀疏特征策略遗忘缓解 VLA 模型的状态幻觉

    提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉

    arXiv
    2610.09496
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA, π0.5
    AbstractSOUL 以稀疏特征遗忘 VLA 状态幻觉。

    SOUL用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。

    Paper analysisRead analysis
  10. 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

    arXiv
    2610.09264
    Published
    Layer
    Application layer
    Setting
    coding agent
    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
  11. DefensesarXiv 2610.09043

    CARE：安全高效的人机协作决策框架

    提出 CARE 框架，在误分类风险约束下减少人机协作的人工查询

    arXiv
    2610.09043
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-VL-2B-Instruct, Perspective, Moderation and others9
    AbstractCARE 以残差校正加逐步校准做人机决策，四个任务上少查询并控制集成风险。

    CARE 是面向人机协同二分类的端到端流水线，要在误分类风险不超过用户容忍的前提下减少人类查询。设定是 i.i.d.数据流、人类 oracle 标签正确、AI 为任意黑盒概率分类器。

    Paper analysisRead analysis
  14. DefensesarXiv 2610.07570

    ProbeGuard：按共识形成过程判断弃答，识别医疗问答中的一致错误

    提出 ProbeGuard，按共识形成过程对医疗问答做选择性弃答

    arXiv
    2610.07570
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-8B, Llama-3.1-8B-Instruct, HuatuoGPT-o1-8B
    AbstractProbeGuard 用共识形成过程做可认证弃权，并在全票层分开答对与答错的共识。

    ProbeGuard 是给多轮共识医学问答用的认证弃权框架：基板照原样作答，弃权只看共识是怎么形成的。

    Paper analysisRead analysis
  15. DefensesarXiv 2610.07403

    针对 LLM 谄媚的纵深防御：记忆门控对激活诱导与记忆诱导谄媚的评估

    评测记忆门控对激活诱导与记忆诱导谄媚的防御效果

    arXiv
    2610.07403
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    Abstract作者称外部记忆过滤成立，数据未显示反向转向再有贡献。

    作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。

    Paper analysisRead analysis
  16. Evaluation and benchmarksarXiv 2610.06748

    BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全

    构建 BazaarBench，评测 C2C 市场中 Agent 的违规与失信行为

    arXiv
    2610.06748
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.5, GPT-5.4, GPT-5.4-mini and others5
    Abstract论文提出挂钩底层资产的 C2C 交易评测基准，发现时间压力与对抗指令显著推高了智能体的违规承诺与欺诈行为。

    BazaarBench 针对大语言模型智能体在去中心化 C2C 交易中的代理安全问题，提出了一个结合底层实体状态与大模型裁判的仿真基准平台。

    Paper analysisRead analysis
  17. DefensesarXiv 2610.05870

    MBZUAI 提出可校准的真实图像认证方法

    提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动

    arXiv
    2610.05870
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    White-box

    Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。

    Paper analysisRead analysis
  18. DefensesarXiv 2610.05826

    研究者提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    arXiv
    2610.05826
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Abstract用截止期限制未核验可见时长。

    这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。

    Paper analysisRead analysis
  19. AttacksarXiv 2610.05793

    研究者训练出按多智能体拓扑触发的代码后门模型

    提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞

    arXiv
    2610.05793
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct

    Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。

    Paper analysisRead analysis
  20. Analysis and theoryarXiv 2610.06163

    SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节

    提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次

    arXiv
    2610.06163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro and others6
    AbstractSAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。

    SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。。

    Paper analysisRead analysis
Load more