Skip to content

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

Oct 12 · Monday

All papers

Found 143 papers
Filter3

Attack type

Jailbreaks6Prompt injection92Poisoning and backdoors45Extraction and theft9Detection evasion15Denial of service3

Attack technique

Gradient and representation optimization4Automated search15Encoding and obfuscation7Role-play and persuasion4Side channels4Defense-targeted5Dormant triggers23

Model risks

Dangerous agent actions5

Defense type

Model hardening4Detection and filtering13Instruction–data separation17Permissions and approval18Monitoring and auditing8Watermarking and provenance8

Impact

Harmful content3Unauthorized actions55Data and privacy leaks24Output manipulation41Availability and reliability4Oversight failure5

System type

Models and APIs25LLM applications20AI Agent98coding agent9web agent5Multi-agent systems13

Attacker access

Black-box9

Attack surface / entry point

User input410Web pages and interfaces69Documents and messages87Tool responses108Tool and skill descriptions63Code repositories and dependencies31Retrieval corpus37Memory writes39Inter-agent messages27Images, audio and video124Training data71Weights and gradients69Distribution channels60Inference services and hardware22

Layer

Model layer13Application layer116Infrastructure layer14

System component

MCP and skills14Memory44RAG5Guardrails and judges13Monitors10Reasoning chains5Permissions and sandboxing16Vision4Embeddings3Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Documents and messagesAttack surface / entry point：Memory writesAttack surface / entry point：Inference services and hardwareClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.11848

    SemField: training-free semantic watermark

    Proposes the semantic watermark SemField, which still identifies the attribution of generated text after paraphrasing and structural changes.

    arXiv
    2610.11848
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.2-1B, Qwen3-1.7B, OPT-1.3B
    AbstractTraining-independent document-level semantic watermark.

    SemField is a zero-bit semantic watermark embedded by the provider at generation time and detected later with a key, used to identify the provider's own model text after paraphrasing and sentence-level structural changes.

    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

    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
  3. AttacksarXiv 2610.09981

    研究：LLM 路由决策日志可推断用户医疗、自伤等敏感话题

    提出利用路由元数据推断敏感话题的侧信道攻击

    arXiv
    2610.09981
    Published
    Layer
    Infrastructure layer
    Setting
    LLM applications
    Evaluated models
    RouteLLM (BERT router), notdiamond-0001, Vela (vLLM Semantic Router)

    Abstract论文揭示并测量了 LLM 路由决策在无文本日志中的敏感话题泄露，验证了按类别公平性防御的有效性与边界。

    Paper analysisRead analysis
  5. 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

    arXiv
    2610.09793
    Published
    Layer
    Application layer
    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
  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

    arXiv
    2610.08951
    Published
    Layer
    Application layer
    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
  8. 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

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    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
  9. 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

    arXiv
    2610.07645
    Published
    Layer
    Application layer
    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
  11. AttacksarXiv 2610.06848

    TranScope：利用 CPU 性能计数器对 Transformer 做成员推断攻击

    提出 TRANSCOPE，用 CPU 硬件计数器推断训练集成员

    arXiv
    2610.06848
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    BERT (4.4M-340M), ViT (22M-307M), Pythia (70M-2.8B) and others5

    AbstractTRANSCOPE 揭示了分词器在嵌入表引发的硬件访问局部性差异，证实微架构计数器可突破恒定时间与置信度遮蔽防御。

    Paper analysisRead analysis
  12. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见

    arXiv
    2610.05894
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct

    Abstract通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。

    Paper analysisRead analysis
  13. InterpretabilityarXiv 2610.05295

    研究用因果追踪区分间接提示注入中的可读信号与有效干预

    用因果追踪区分间接提示注入中的角色可读性与有效干预

    arXiv
    2610.05295
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen-2.5-7B, Qwen-2.5-1.5B, Llama-3.1-8B and others8
    Abstract作者称源角色先于强工具选择效应可读，有效编辑还取决于位置、长度和方向来源。

    在权重固定的白盒模型上，源角色可以先被读出。沿相关方向的编辑是否改变行为，要在目标位点上另测。。

    Paper analysisRead analysis
  14. AttacksarXiv 2610.05266

    论文披露主动式智能体的服务方间接提示注入攻击

    提出服务方间接提示注入，把主动智能体的决策协助转向预选目标

    arXiv
    2610.05266
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5, Claude Opus 4.6, Gemini 3 Pro and others7
    Abstract提供者侧间接注入用 T–B–S 把主动协助转向外部目标，并在三环境中提高模拟用户授权。

    外部提供者只控制与自身目标关联的内容，就可以把良性主动个人智能体的协助转向该目标。

    Paper analysisRead analysis
  15. DefensesarXiv 2610.05163

    Researchers construct segmented prompt injection on Claude Code and Codex and release a boundary action audit benchmark

    提出 PAA 方法，在边界动作前审计长流程智能体的分阶段提示注入

    arXiv
    2610.05163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (v2.1.172, Claude Sonnet 5), Codex CLI (v0.144.0, GPT-5.5)
    Abstract论文针对长流程注入提出边界动作审计与 PAA，在保持低误阻的同时实现高拦截率。

    本研究针对长流程智能体在执行任务时面临的分阶段间接提示注入威胁，提出了在动作生效前进行拦截的边界动作审计框架与路径对齐归因方法。

    Paper analysisRead analysis
  17. DefensesarXiv 2610.04763

    UT Austin 将 SynthID 水印嵌入基因组语言模型，凭 DNA 序列和密钥追溯 AI 生成片段

    把 SynthID 嵌入基因组语言模型采样，并用位置无关检测追溯生成序列

    arXiv
    2610.04763
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Carbon-500M, GENERator-v2-eukaryote-1.2b-base
    Abstract两个六碱基基因组模型嵌入 SynthID 后，位置无关验证能找回水印，作者称这只是统计检测。

    作者在两个六碱基基因组模型的采样里嵌入 SynthID，并让验证者在不知道起点、链和 token phase 时做一次校正后的检出。

    Paper analysisRead analysis
  18. 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

    arXiv
    2610.04589
    Published
    Layer
    Application layer
    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
Load more