Skip to content

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

Oct 12 · Monday

All papers

Found 113 papers
Filter5

Attack type

Jailbreaks6Prompt injection73Poisoning and backdoors22Extraction and theft9Detection evasion12

Attack technique

Automated search13Encoding and obfuscation3Reasoning-chain manipulation3Side channels3Defense-targeted4Dormant triggers10

Model risks

Dangerous agent actions4

Defense type

Model hardening3Detection and filtering8Instruction–data separation12Permissions and approval12Monitoring and auditing8Watermarking and provenance9

Impact

Unauthorized actions51Data and privacy leaks19Output manipulation22Oversight failure7

System type

Models and APIs27LLM applications21AI Agent86coding agent23web agent4Browser and computer use3Multi-agent systems8

Attacker access

Black-box8

Attack surface / entry point

User input390Web pages and interfaces62Documents and messages70Tool responses106Tool and skill descriptions63Code repositories and dependencies29Retrieval corpus14Memory writes41Inter-agent messages28Images, audio and video120Training data70Weights and gradients72Distribution channels62Inference services and hardware20

Layer

Model layer13Application layer85Infrastructure layer13

System component

MCP and skills9Memory16Guardrails and judges6Monitors10Reasoning chains5Permissions and sandboxing15Vision3Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：AI AgentAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Inference services and hardwareClear all

Another 240papers 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
  3. 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
  4. 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
  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
  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

    arXiv
    2610.07510
    Published
    Layer
    Application layer
    Setting
    coding agent
    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
  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. 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
  14. 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
  16. 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
  19. 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
  20. 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
Load more