Story
arxiv_cs_cl · Nov 5, 2026 · paper
Source brief
Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks
arxiv.orgNov 5, 2026
original source linked
In brief
Personal AI agents face social engineering attacks supported by forged multimodal content, but existing evaluations mainly focus on text-based dialogue, leaving their intrinsic security under such attacks insufficient...
Feed lens
agentharnessevaluation