Skip to content

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

Oct 13 · Tuesday

All papers

Found 21 papers
Filter5

Attack type

Prompt injection13Poisoning and backdoors7

Defense type

Detection and filtering5Instruction–data separation5

Impact

Unauthorized actions7Output manipulation12

System type

Models and APIs65LLM applications13AI Agent97coding agent23web agent22Browser and computer use8Multi-agent systems6Embodied systems and robotics3

Attack surface / entry point

User input35Web pages and interfaces15Documents and messages20Tool responses5Code repositories and dependencies3Retrieval corpus25Images, audio and video10Training data3Inference services and hardware3

Layer

Application layer18Training and data layer3

System component

RAG4Guardrails and judges6Vision5Multimodal5
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.
System type：LLM applicationsSystem type：Browser and computer useAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Training dataClear all

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

  2. 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
  4. DefensesarXiv 2610.03089

    COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks

    提出 COBRA 双 LLM 架构，防御计算机使用 Agent 的分支转向攻击

    arXiv
    2610.03089
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    gpt-5, UI-TARS-1.5-7B, claude-sonnet-5 and others6

    Abstract提出分支转向防御架构 COBRA，通过事前能力约束与边界代理消除分支转向攻击并兼顾效用。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2610.06898

    DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准

    用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性

    arXiv
    2610.06898
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Qwen2.5-VL(32B), Qwen3-VL(32B), GUI-Owl(32B) and others7

    Abstract论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。

    Paper analysisRead analysis
  8. AttacksarXiv 2609.02774

    CodePoisonRAG：针对检索增强代码生成的知识投毒攻击

    提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞

    arXiv
    2609.02774
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B

    AbstractCodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2609.02316

    Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

    构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御

    arXiv
    2609.02316
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Gemma-4-31B-IT, Qwen-3.5-35B-A3B, Llama-4-Scout-17B-16E and others8

    Abstract论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。

    Paper analysisRead analysis
  10. Evaluation and benchmarksarXiv 2609.05535

    Mind2Web-Injection：面向网页 Agent 视觉提示注入护栏的证据对齐评测

    提出 Mind2Web-Injection 评测网页 Agent 视觉注入护栏

    arXiv
    2609.05535
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-5.6-luna, Qwen3-VL-32B, Qwen3-VL-8B and others6
    Abstract作者称检测、定位和反事实响应在六个 VLM 上可分开。

    Mind2Web-Injection 用来检查网页截图护栏的判决是否对齐到该用的画面证据。。

    Paper analysisRead analysis
  12. Evaluation and benchmarksarXiv 2608.16824

    GEO-Flag：检测与测量面向生成式引擎优化的网页内容

    提出 GEOFlagBench 与 IPT，检测并测量生成式引擎优化网页

    arXiv
    2608.16824
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    ModernBERT-base, Qwen3-0.6B, Gemini-3.5-flash and others11
    AbstractGEOFlagBench 与 IPT 用于检测 GEO 页，并估计真实检索中的占比与引用可核验性。

    GEO-Flag 把页面级 GEO 检测做成可评测任务，并在发布的检索结果上估计被判为 GEO 的页面占比。

    Paper analysisRead analysis
  13. DefensesarXiv 2608.06422

    CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用

    提出分片监督，将评判标准分配给独立调用以抵御展示攻击

    arXiv
    2608.06422
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Opus 4.6 and others4
    Abstract论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。

    本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。

    Paper analysisRead analysis
  14. AttacksarXiv 2605.24421

    研究者提出日志型提示注入攻击，可抑制 SOC 中 LLM 分析助手的恶意日志识别

    提出日志基底提示注入，操纵 SOC 分析员的分类、摘要与处置建议

    arXiv
    2605.24421
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    gpt-4o-mini

    Abstract在 gpt-4o-mini 上，人格劫持与上下文操纵可改写 SOC 分析输出，直接覆盖在分类上无效。

    Paper analysisRead analysis
  15. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  16. Evaluation and benchmarksarXiv 2604.02947

    AgentHazard：评估计算机使用智能体有害行为的基准

    提出 AgentHazard 基准，评测计算机使用智能体的执行层有害行为

    arXiv
    2604.02947
    Published
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen2.5-72B-Instruct, Qwen2.5-Coder-32B-Instruct, Qwen3-32B and others12
    AbstractAgentHazard 评估了计算机使用智能体的执行安全，作者认为模型层对齐无法可靠保障智能体层面的安全性。

    AgentHazard 是针对计算机使用智能体执行层安全构建的评估基准，重点探究多步工具调用下局部合理动作累积引发的危害。

    Paper analysisRead analysis
  17. DefensesarXiv 2602.10915

    Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

    Proposes Aura, which uses a trusted kernel to mediate the identity, perception, and action control of mobile agents

    arXiv
    2602.10915
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Gemini-3-Flash
    AbstractAura mediates structured interactions via the Agent Kernel.

    Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants..

    Paper analysisRead analysis
  19. AttacksarXiv 2602.05484

    Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection

    提出隐蔽提示注入攻击 LLM 钓鱼检测器，并给出防御 InjectDefuser

    arXiv
    2602.05484
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    OpenAI GPT-5, xAI Grok 4 Fast (Non-Reasoning), Meta Llama 4 Maverick and others4
    Paper analysisRead analysis
Load more