Justin Tan, Miao Li, Ding Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31404 · open-access PDF
Phishing stellt daher Datenschutz- und Sicherheitsrisiken dar, die nicht nur davon abhängen, ob Agenten bösartige Nachrichten erkennen, sondern auch davon, wie sie reagieren. Bestehende Phishing-Datensätze wurden hauptsächlich für die konventionelle Erkennung entwickelt, wodurch die Anfälligkeit von Agenten für überzeugende bösartige Anfragen unzureichend charakterisiert ist.
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