Publications & Research
Peer-reviewed publications, conference papers, and research collaborations
Deepfake Attacks on Biometric Recognition: Evaluation of Resistance to Injection Attacks
IEEE UEMCON 2024 · Presented at IBM T.J. Watson Research CenterThis paper evaluates the robustness of biometric systems under injection attacks using deepfake voice and image inputs, highlighting challenges and proposing mitigation strategies.
View PublicationFace Liveness Detection Competition (LivDet-Face) - 2024
2024 IEEE International Joint Conference on Biometrics (IJCB)This paper presents the results of the LivDet-Face 2024 competition, a benchmark event for evaluating face Presentation Attack Detection (PAD) systems. It analyzes cutting-edge algorithms and systems designed to detect spoofing attempts using a standardized dataset and evaluation protocol.
View PublicationExtended-Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition (ELAD-SVDSR)
To be published · Department of Electrical and Computer Engineering, Clarkson UniversityThis paper introduces ELAD-SVDSR, a robust dataset aimed at advancing synthetic voice (DeepFake) detection and automatic speaker recognition. It includes ~45-minute recordings from 36 participants using five different microphones, along with synthetic voice samples generated from 20 subjects using both open-source and commercial tools. The dataset supports text-dependent modeling and contains detailed metadata on speaker demographics and recording conditions. ELAD-SVDSR is poised to enable cutting-edge research in biometric security, voice authentication, and audio forensics.