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
Filter4
Attack type
Impact
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Another 233papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2608.04565
Researchers propose Breadcrumbing long-range attack that can hijack the evidence chain of DeepResearch-style search agents
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
Adversarial attacks against modern vision-language models
Conduct adversarial attacks on product images for open-source visual shopping agents and induce wrong purchases
- 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
AbstractThe authors state that LLaVA is easily induced by three attacks to buy the wrong item, while Qwen's correct purchase rate remains close to its clean condition.
The authors compare the robustness of two open-source VLM shopping agents against image adversarial perturbations in a self-built e-commerce environment.
MalURLBench: A benchmark for evaluating agent vulnerabilities when processing web URLs
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
- AttacksarXiv 2601.13612
PINA：针对导航智能体的提示注入攻击
提出 PINA，迭代优化针对导航智能体的提示注入
- arXiv
- 2601.13612
- Published
- Layer
- Application layer
- Evaluated models
- GPT-3.5-turbo, GPT-4, Balcı et al. [2]
- AttacksPrompt injection
- TechniqueAutomated search
AbstractPINA 在黑盒下优化导航提示注入。
PINA 是面向基于 LLM 的导航智能体、在黑盒条件下优化提示注入的框架。
You have reached the end