PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks

TL;DR

This paper introduces PhySE, a framework for real-time AR-LLM social engineering attacks that uses rapid profile generation and adaptive psychological strategies, addressing delays and static tactics in existing methods.

Contribution

It presents a novel VLM-based social context training method and an adaptive psychological agent for dynamic, theory-based social engineering in AR-LLM attacks.

Findings

Pre-trained VLM enables rapid profile formation in real-time interactions.

Adaptive psychological strategies outperform static tactics in social engineering effectiveness.

User study with 60 participants and 360 conversations validates the framework's effectiveness.

Abstract

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 Model (LLM) then analyzes this data to identify the individual and generate a detailed social profile. Subsequently, LLM-powered agents employ social engineering strategies, providing real-time conversation suggestions, to gain the target trust and ultimately execute phishing or other malicious acts. Despite its potential, the practical application of AR-LLM-SE faces two major bottlenecks, (1) Cold-start personalization, Current Retrieval-Augmented Generation (RAG) methods introduce critical delays in the earliest turns, slowing initial profile formation and disrupting real-time interaction, (2) Static Attack Strategies, Existing approaches rely on fixed-stage, handcrafted social engineering tactics that lack foundation in established psychological theory. To address these limitations, we propose PhySE, a novel framework with two core innovations, (1) VLM-Based SocialContext Training, To eliminate profiling delays, we efficiently pre-train a Visual Language Model (VLM) with social-context data, enabling rapid, on-the-fly profile generation, (2) Adaptive Psychological Agent, We introduce a psychological LLM that dynamically deploys distinct classes of psychological strategies based on target response, moving beyond static, handcrafted scripts. We evaluated PhySE through an IRB-approved user study with 60 participants, collecting a novel dataset of 360 annotated conversations across diverse social scenarios.