Saved in:
Bibliographic Details
Main Authors: Yu, Tianlong, Yang, Yang, Zhou, Ziyi, Xu, Jiaying, Li, Siwei, Guan, Tong, Wang, Kailong, Bi, Ting
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.23148
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917436558671872
author Yu, Tianlong
Yang, Yang
Zhou, Ziyi
Xu, Jiaying
Li, Siwei
Guan, Tong
Wang, Kailong
Bi, Ting
author_facet Yu, Tianlong
Yang, Yang
Zhou, Ziyi
Xu, Jiaying
Li, Siwei
Guan, Tong
Wang, Kailong
Bi, Ting
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_23148
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks
Yu, Tianlong
Yang, Yang
Zhou, Ziyi
Xu, Jiaying
Li, Siwei
Guan, Tong
Wang, Kailong
Bi, Ting
Artificial Intelligence
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.
title PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks
topic Artificial Intelligence
url https://arxiv.org/abs/2604.23148