all InfoSec news
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
April 26, 2024, 4:10 a.m. | Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala, Bimal Viswanath
cs.CR updates on arXiv.org arxiv.org
Abstract: Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly available deepfake datasets. In this work, we study 8 state-of-the-art detectors and argue that they are far from being ready for deployment due to two recent developments. First, the emergence of lightweight methods to customize large generative models, can enable an attacker to create …
analysis art arxiv cs.cr cs.cv cs.lg datasets deepfake deepfake images detect detection generative generative models image images online platforms performance platforms research risks serious state study synthetic threat threat landscape work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Director, Cyber Risk
@ Kroll | South Africa
Security Engineer, XRM
@ Meta | New York City
Security Analyst 3
@ Oracle | Romania
Internship - Cyber Security Operations
@ SES | Betzdorf, LU
Principal Product Manager (Network/Security Management) - NetSec
@ Palo Alto Networks | Bengaluru, India
IT Security Engineer
@ Timocom GmbH | Erkrath, Germany