4 papers · 1 filter
Faithful Dual-constrained Erasure for Robust LLM Safety Alignment
Jiaqing Li, Shide Zhou, Zhibo Zhang +3
Machine unlearning has emerged as a crucial mechanism for removing hazardous knowledge and enforcing safety alignment in Large Language Models (LLMs). However, recent studies revea…
UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks
Tianlong Yu, Yang Yang, Xiao Luo +6
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 A…
When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion
Jiaqing Li, Zhibo Zhang, Shide Zhou +3
Model merging has emerged as a powerful technique for combining specialized capabilities from multiple fine-tuned LLMs without additional training costs. However, the security impl…
On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks
Ting Bi, Chenghang Ye, Zheyu Yang +8
Augmented Reality (AR) and Multimodal Large Language Models (LLMs) are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integra…