Skip to content

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

Oct 12 · Monday

All papers

Found 10 papers
Filter5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

Another 254papers 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. DefensesarXiv 2610.07403

    针对 LLM 谄媚的纵深防御:记忆门控对激活诱导与记忆诱导谄媚的评估

    评测记忆门控对激活诱导与记忆诱导谄媚的防御效果

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    Abstract作者称外部记忆过滤成立,数据未显示反向转向再有贡献。

    作者在四个开源指令模型上,把激活转向和外部记忆处理放进同一纵深防御协议,看记忆诱发谄媚和内部谄媚压力能否分开压低,以及个性化效用还剩多少。要处理的问题是:检索到的用户历史会推动模型顺从存储信念。只改外部上下文,并不直接动模型内部的谄媚表征。

    Paper analysisRead analysis
  3. A study empirically tests five Agent memory systems and finds none of them enforce revocation markers

    评测 Agent 记忆系统的软撤回执行情况,并提出陈旧检索防护

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-5.5, Grok-4, DeepSeek-V4-Flash and others9

    Abstract系统揭示了记忆系统软撤回在检索时普遍未执行的安全漏洞,证明写回会击穿现有防御,并提出读取端防护作为必要控制手段。

    Paper analysisRead analysis
  4. 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
  5. 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
  6. No Attacker Needed: Unintentional Cross-User Contamination in Shared-State LLM Agents

    形式化并评测共享状态 Agent 的无意跨用户污染

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-4o
    Abstract作者报告良性交互即可造成跨用户污染,文本清洗挡不住代码记忆。

    UCC 是共享状态 LLM 智能体上的稳健性问题:源交互可以是良性的,局部有效的制品仍会在后来被误用到其他用户。

    Paper analysisRead analysis
  7. DefensesarXiv 2603.14707

    视觉混淆代理:利用与防御计算机使用智能体的感知失效

    提出进程外双通道对比分类,拦截计算机使用智能体的错误点击

    Published
    Evaluated models
    multi-modal-embed-small
    Abstract感知错误可被屏幕像素对调利用。

    作者把 CUA 的感知失败写成安全漏洞visual confused deputy:智能体按看错的屏幕授权 click(x,y),真实落点与它以为的元素不一致。

    Paper analysisRead analysis
  8. 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