PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks
PhySE uses visual language models to enable real-time, adaptive social engineering through AR wearable devices.
The emerging threat of AR-LLM-based Social Engineering (AR-LLM-SE) attacks (e.g. SEAR) poses a significant risk to real-world social interactions. In such an attack, a malicious actor uses Augmented Reality (AR) glasses to capture a target visual and vocal data. A Large Language ...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
The PhySE framework demonstrates how merging high-speed visual profiling with adaptive psychological modeling dramatically increases the efficacy of real-time social engineering. This evolution represents a critical shift from static scripts to dynamic manipulation, highlighting urgent security vulnerabilities in current wearable AR technology.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.