Wenqi Wei

Bio:
Dr. Wenqi Wei is a tenure-track assistant professor in the Department of Computer and Information Sciences at Fordham University. He was a Research Staff Member at IBM Research and got his PhD in the School of Computer Science, Georgia Institute of Technology. His research interests include trustworthy AI, data privacy, machine learning service, and big data analytics. His research has appeared on major cybersecurity, data mining, and AI venues, including CCS, CVPR, IJCAI, theWebConf, IEEE TDSC, IEEE TIFS, and ACM CSUR. He is an associate editor of ACM Transactions on Internet Technology.

Abstract:
Recent advances in Text-to-Speech (TTS) and Voice-Conversion (VC) using generative Artificial Intelligence (AI) technology have made it possible to generate high-quality and realistic human-like audio. This introduces significant challenges to distinguishing AI-synthesized speech from the authentic human voice and could raise potential issues of misuse for malicious purposes such as impersonation and fraud, spreading misinformation, deepfakes, and scams. However, existing detection techniques for AI-synthesized audio have not kept pace and often exhibit poor generalization across diverse datasets. To address this gap, this research aims to uniformly benchmark AI-audio detection across both traditional and foundation model-based deepfake detection systems, shedding lights on developing a fine-grained audio deepfake audio detection system capable of identifying AI-generated segments.