Skip to content

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

Oct 13 · Tuesday

All papers

Found 62 papers
Filter6

Attack type

Jailbreaks3Prompt injection26Poisoning and backdoors24Extraction and theft9Detection evasion12

Attack technique

Automated search8Encoding and obfuscation5Side channels3Defense-targeted6Dormant triggers5Selection manipulation3

Defense type

Detection and filtering7Instruction–data separation4Permissions and approval3Monitoring and auditing3Watermarking and provenance7

Impact

Unauthorized actions20Data and privacy leaks13Output manipulation12Oversight failure3

System type

Models and APIs27LLM applications22AI Agent120coding agent28web agent5Browser and computer use3Multi-agent systems9

Attacker access

Black-box5

Attack surface / entry point

User input317Web pages and interfaces5Documents and messages19Tool responses16Tool and skill descriptions27Code repositories and dependencies21Retrieval corpus6Memory writes10Inter-agent messages25Images, audio and video102Training data68Weights and gradients69Distribution channels39Inference services and hardware19

Layer

Model layer13Application layer35Infrastructure layer13

System component

MCP and skills23Memory4Guardrails and judges4Monitors7Permissions and sandboxing4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Inference services and hardwareClear all

Another 227papers 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. AttacksarXiv 2610.10612

    PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

    提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器

    arXiv
    2610.10612
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    CISCO, HSS, AUDITOR and others8
    Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。

    这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。

    Paper analysisRead analysis
  6. 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
  7. Analysis and theoryarXiv 2610.06001

    AgentSpy: Observing AI agent behavior at the system call layer and detecting skill injection attacks

    提出 AgentSpy，在系统调用层观测 Agent 行为并检测技能注入

    arXiv
    2610.06001
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    gpt-5.6-terra, deepseek-v4-flash, glm-5.3-flash and others4
    Abstract提出了系统级智能体监控框架 AgentSpy，揭示出通过测试背后的非预期行为与注入风险。

    本研究提出了面向 AI 智能体的系统级外部监控与行为分析框架 AgentSpy。

    Paper analysisRead analysis
  8. 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
  9. 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
  10. 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
  12. Analysis and theoryarXiv 2610.02504

    HXAI：分布式能源系统中的分层隐私保护可解释 AI 框架

    提出 HXAI 分层隐私解释框架，本地保留细解释并只发布加噪摘要

    arXiv
    2610.02504
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    gradient-boosted tree regression models
    AbstractHXAI 把无噪声局部 SHAP 留在家庭内，只聚合差分隐私摘要。

    HXAI 是面向分布式能源系统的分层隐私保护解释框架，服务规划、监测与诊断，而不是实时控制。

    Paper analysisRead analysis
  13. DefensesarXiv 2610.02349

    MIRROR：面向多智能体通信的法定人数完整性防御

    提出 MIRROR，用多路径摘要多数表决保障多智能体通信完整性

    arXiv
    2610.02349
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemma-4-31B-it, Gemini 2.5 Pro
    AbstractMIRROR 靠多数路径。

    MIRROR 是 LLM 多智能体通信层上的多路径法定人数完整性原语，只处理不透明字节，不解释消息内容。要处理的是 Agent-in-the-Middle：中介合法终结 TLS 后可改在途消息，而语义校验有推理开销和误拦，签名又要求私钥管理。做法是生成结束后复制同一规范化载荷。

    Paper analysisRead analysis
  14. AttacksarXiv 2609.39352

    研究者提出解耦铺垫与执行的 LLM Agent 技能投毒攻击

    提出 CoordPoison，解耦技能投毒的借口与动作

    arXiv
    2609.39352
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    DeepSeek-V4-Flash, GLM-5.3-Flash, Claude-Sonnet-4.6 and others5
    AbstractCoordPoison 外置借口。

    CoordPoison 是一种 Skill 供应链投毒方法，把“为何执行”和“执行什么”拆到两个 Skill。。

    Paper analysisRead analysis
  15. Evaluation and benchmarksarXiv 2609.39146

    MADBench：多智能体辩论安全性评测基准发布

    提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响

    arXiv
    2609.39146
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gpt-4o, GPT-5, GPT-6 Astra
    AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。

    MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。

    Paper analysisRead analysis
  16. 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

    arXiv
    2609.38270
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    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
  17. DefensesarXiv 2609.37310

    AutoMark：让自动研究流程自主发现更优 LLM 水印方案

    提出 AutoMark，自动搜索并统计检验 LLM 文本水印

    arXiv
    2609.37310
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen3.8-27B, GPT-6 Astra and others5
    AbstractAutoMark 的贡献同时包含搜索出的水印，以及用于约束自动研究误报与评测漏洞的验证框架。

    AutoMark 是一套自动水印研究框架：先检查生成分布和误报性质，再比较检测、编辑鲁棒性与质量，最后人工分析组件并做留出评测。

    Paper analysisRead analysis
  18. Evaluation and benchmarksarXiv 2609.36817

    pikit：面向间接提示注入研究与评测的可组合工具包

    构建可组合工具包 pikit，评测编码智能体的间接提示注入

    arXiv
    2609.36817
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstractpikit 提供组合式间接注入评测。

    pikit 是面向间接提示注入研究的组合式工具包，主要贡献是组织攻击、投递通道、防御和判定流程，而非提出新的攻击优化算法。

    Paper analysisRead analysis
  20. DefensesarXiv 2609.36372

    TTMark：超越单 token 熵的成对无失真水印

    提出成对无失真水印 TTMARK，增强低熵下的机器文本检测

    arXiv
    2609.36372
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama3.2-3B-Instruct, Mistral-v0.3-7B-Instruct, Qwen2.5-7B-Instruct
    AbstractTTMARK 用水印化相邻 token 对利用条件熵，在多种无失真方案上提高检测并保持生成质量。

    TTMARK 是一种成对、无失真的文本水印：对相邻 token 的联合分布重加权，而不是逐 token 独立重加权。

    Paper analysisRead analysis
Load more