all InfoSec news
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection
June 25, 2024, 4:20 a.m. | Hyun Myung Kim, Kangwook Jang, Hoirin Kim
cs.CR updates on arXiv.org arxiv.org
Abstract: As speech synthesis systems continue to make remarkable advances in recent years, the importance of robust deepfake detection systems that perform well in unseen systems has grown. In this paper, we propose a novel adaptive centroid shift (ACS) method that updates the centroid representation by continually shifting as the weighted average of bonafide representations. Our approach uses only bonafide samples to define their centroid, which can yield a specialized centroid for one-class learning. Integrating our …
arxiv audio audio deepfake class continue cs.cr cs.sd deepfake deepfake detection detection eess.as novel remarkable representation speech synthesis systems updates
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Principal QA Engineer - Data Storage and Ingestion pipelines (Cortex)
@ Palo Alto Networks | Tel Aviv-Yafo, Israel
Principal Software Engineer - .NET / API
@ Commonwealth Bank | Sydney, NSW - CBP South, 11 Harbour Street
AVP | Governance
@ MUFG | Watermark - 410 North Scottsdale Road
Tech Lead - Full Stack - Défense & Sécurité - Lille
@ Sopra Steria | Villeneuve-d'Ascq, France
Windows / Linux Systems Administrator
@ General Dynamics Information Technology | USA FL MacDill AFB - MacDill AFB (FLC007)
Graduate Software Engineer (C, C++)- HP Wolf Security
@ HP | UKC01 - Cambridge, United Kingdom (UKC01)