Skip to content

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

Oct 12 · Monday

All papers

Found 19 papers

Another 240papers do not have category tags yet and are not included in filtered results.

  1. 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

    Published
    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
  2. Study retests 15 prompt injection detectors: benchmark scores poorly predict agent deployment performance

    重测提示注入检测器在 Agent 工具输出上的检出与任务阻断

    Published
    Setting
    AI Agent
    Evaluated models
    Horizon-Labs, Wolf Defender, Prismor-1.5B and others15

    Abstract论文揭示公开基准无法反映智能体检测器表现,检测能力源于输入格式相似而非通用防御,建议基于工具输出与低误报评测。

    Paper analysisRead analysis
  3. Agentic Commerce Bench:衡量会花钱的智能体的欺诈检测能力

    构建支付欺诈基准 ACB,评测花钱智能体的欺诈检测

    Published
    Setting
    AI Agent
    Evaluated models
    gordonguard, pattern judge
    AbstractACB 把支付欺诈与智能体操纵分开测量,作者强调观察权限、误报预算和微支付复核成本。

    ACB 是一套智能体支付欺诈基准与检测参考栈,目标是衡量钱是否被不当提取,而不仅是智能体是否接受了恶意指令。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.33039

    TACIT: detecting agent trajectory harm from LLM internal states

    提出 TACIT,从冻结内部状态检测智能体有害轨迹

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen3-4B, Llama-3.1-8B, Qwen3-4B-Instruct and others4

    Abstract提出基于内部表征的智能体轨迹安全检测方法 TACIT,揭示工具风险表征特性并在多项基准上提升检测表现与效率。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.22510

    特拉维夫大学提出爆炸性提示词:条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词,并设计摄入期检测器 DeFuse

    Published
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具,提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁,研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
  6. 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

    Published
    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
  7. 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

    Published
    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
  8. 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

    Published
    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
  9. AttacksarXiv 2607.06595

    When Agents Remember Too Much: Memory Poisoning Attacks against Large Language Model Agents

    Proposed GhostWriter memory poisoning, which writes into the agent's long-term memory via email and calendar and activates across sessions

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
    Paper analysisRead analysis
  10. DefensesarXiv 2603.14707

    Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents

    Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents

    Published
    Evaluated models
    multi-modal-embed-small
    AbstractPerception errors can be exploited by swapping screen pixels.

    The authors frame CUA's perception failure as a security vulnerability, visual confused deputy: the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.

    Paper analysisRead analysis
  11. DefensesarXiv 2601.10156

    ToolSafe 提出步骤级护栏 TS-Guard 与 TS-Flow,降低 Agent 有害工具调用

    提出 TS-Guard 与 TS-Flow,在执行前检测并引导 Agent 修正有害工具调用

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-4o, TS-Guard, Qwen2.5-14B-Instruct
    AbstractTS-Bench 标步骤级风险,TS-Guard 用多任务 RL 做执行前判定,TS-Flow 用反馈代替直接中止。

    ToolSafe 研究 LLM 智能体在工具执行前的步骤级安全:基准 TS-Bench、护栏 TS-Guard,以及反馈驱动框架 TS-Flow。

    Paper analysisRead analysis
  12. WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    Published
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测:显式线索可被部分检出,隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击:攻击者改网页,使智能体执行目标动作,而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end