微软研究院发布 CAVEAT
提出 CAVEAT 基准，评测激励失配市场中计算机使用 Agent 的购买决策退化
- arXiv
- 2609.27273
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- GPT-5.6-Sol, GPT-5.6-Terra, GPT-5.6-Luna and others14
Abstract提出 CAVEAT 基准揭示智能体在商业偏好下的决策退化，诊断出三类失效并给出缓解方案。
All papers
Filter3
Attack type
Impact
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Another 261papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2608.04565
研究者提出 Breadcrumbing 长程攻击，可劫持 DeepResearch 类搜索 Agent 的证据链
提出权威链劫持与轨迹引导策略演化，劫持搜索 Agent 的证据链
- arXiv
- 2608.04565
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- Qwen3.5-9B, Gemma4-31B, DeepResearch and others7
- AttacksPrompt injection
- TechniqueAutomated search
- ComponentRAG
Abstract论文揭示了多步搜索智能体在受限中间人操纵下的脆弱性，提出 ACH 策略与 TGSE 演化方法并完成系统验证。
MisKnow-Agent 评测
用 MisKnow-Agent 评测深度研究智能体是否采纳误导文档结论
- arXiv
- 2607.20891
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- DeerFlow, WebThinker, Gemini Deep Research and others6
- AttacksPrompt injection
- ComponentRAG
Abstract论文通过 MisKnow-Agent 框架评估发现长程研究智能体易采纳误导性知识，且现有防御难以完全消除该现象。
- AttacksarXiv 2603.16960
针对现代视觉语言模型的对抗攻击
对开源视觉购物智能体实施商品图对抗攻击并诱导买错
- arXiv
- 2603.16960
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- LLaVA-v1.5-7B, Qwen2.5-VL-7B
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
Abstract作者称 LLaVA 易被三种攻击诱导买错，Qwen 正确购买率仍接近其干净条件。
作者在自建电商环境里比较两个开源 VLM 购物智能体对图像对抗扰动的鲁棒性。
MalURLBench：评估 Agent 处理网页 URL 时脆弱性的基准
提出 MalURLBench 评测 Agent 是否接受结构伪装的恶意 URL
- arXiv
- 2601.18113
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- GPT-3.5-Turbo, GPT-4o-mini, GPT-4o and others13
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
You have reached the end