Justin Tan, Miao Li, Ding Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31404 · open-access PDF
计算机使用代理人越来越多地处理隐私信息,并代表用户在桌面和Web应用程序中采取行动,包括电子邮件。因此,诈骗行为带来了隐私和安全风险,这不仅取决于代理人是否识别恶意消息,而且还取决于他们如何响应。现有诈骗数据集主要用于常规检测,使代理人对说服恶意请求的敏感性不够特征。
Machine translation (Meta M2M100); the English original follows.
Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing therefore poses privacy and security risks that depend not only on whether agents recognize malicious messages, but also on how they respond. Existing phishing datasets were developed primarily for conventional detection, leaving agent susceptibility to persuasive malicious requests insufficiently characterized. To expose vulnerabilities that pre-existing datasets may miss, we introduce AgentPhishing, a benchmark for evaluating whether persuasive p
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31404, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange