PulseAugur
LIVE 04:22:18
research · [2 sources] ·
0
research

Researchers unveil defenses against AR-LLM social engineering attacks

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have developed two new frameworks to combat social engineering attacks that leverage augmented reality (AR) and large language models (LLMs). The first, PhySE, uses a visual language model for rapid profile generation and an adaptive psychological agent to tailor social engineering strategies in real-time. The second, UNSEEN, offers a cross-stack defense combining access control on AR devices, LLM unlearning for profile suppression, and runtime agent guardrails. Both frameworks were evaluated in IRB-approved user studies involving 60 participants and 360 annotated conversations. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces novel defense mechanisms against sophisticated AR-LLM social engineering, potentially influencing future security protocols.

RANK_REASON Two academic papers proposing novel frameworks for defense against AR-LLM social engineering attacks.

Read on arXiv cs.AI →

COVERAGE [2]

  1. arXiv cs.AI TIER_1 · Tianlong Yu, Yang Yang, Ziyi Zhou, Jiaying Xu, Siwei Li, Tong Guan, Kailong Wang, Ting Bi ·

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

    arXiv:2604.23148v1 Announce Type: new 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…

  2. arXiv cs.AI TIER_1 · Tianlong Yu, Yang Yang, Xiao Luo, Lihong Liu, Fudu Xing, Zui Tao, Kailong Wang, Gaoyang Liu, Ting Bi ·

    UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

    arXiv:2604.23141v1 Announce Type: cross Abstract: Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR (Augmented Reality) glass to capture the image a…

RELATED ENTITIES

RELATED TOPICS