Menu

A new benchmark conned every frontier AI agent it tested.
📰

A new benchmark conned every frontier AI agent it tested.

DEV Community: cybersecurity·Ganesh Sivakumar·9 days ago
#L7Vvs1AG
#devtocybersecurity#devto#dev#agents#arxiv
Reading 0:00
15s threshold

A research team at the Hong Kong University of Science and Technology built Multimodal-SEA, a benchmark (published as an arXiv preprint) that lets attackers socially engineer personal AI agents the way criminals con people: impersonating a spouse or colleague, building trust, then asking for money or data, backed by forged screenshots, documents, websites and videos. Its 608 task instances are expert-designed from real fraud cases across 14 domains, split into Chinese (316) and English (292) contexts. Every one of the seven frontier multimodal models tested - including Claude, GPT, Gemini, Kimi, Qwen, MiniMax and GLM variants acting as agents - was vulnerable.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.