Justin Tan, Miao Li, Ding Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31404 · open-access PDF
Agen penggunaan komputer semakin menangani informasi pribadi dan bertindak atas nama pengguna di seluruh aplikasi desktop dan web, termasuk email. Phishing karena itu menimbulkan risiko privasi dan keamanan yang tergantung tidak hanya pada apakah agen mengenali pesan berbahaya, tetapi juga pada bagaimana mereka merespon. Dataset phishing yang ada dikembangkan terutama untuk deteksi konvensional, meninggalkan kecenderungan agen untuk meminta-minta berbahaya yang meyakinkan tidak cukup ditandai.
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