July 19, 2022, 1:20 a.m. | Yihao Huang, Felix Juefei-Xu, Qing Guo, Yang Liu, Geguang Pu

cs.CR updates on arXiv.org arxiv.org

The current high-fidelity generation and high-precision detection of DeepFake
images are at an arms race. We believe that producing DeepFakes that are highly
realistic and ``detection evasive'' can serve the ultimate goal of improving
future generation DeepFake detection capabilities. In this paper, we propose a
simple yet powerful pipeline to reduce the artifact patterns of fake images
without hurting image quality by performing implicit spatial-domain notch
filtering. We first demonstrate that frequency-domain notch filtering, although
famously shown to be effective …

deepfake deepfake detection detection domain notch

Senior Associate, Cybersecurity Operations

@ Ares Management Corporation | Los Angeles, CA - CULVER CITY

Senior DevSecOps Engineer

@ Peraton | Fort Gordon, GA, United States

Senior DevSecOps Engineer

@ Diverto | Zagreb, Croatia

Lead DevSecOps Engineer

@ DTCC | Tampa, FL, United States

Incident Responder (Fraud Threat Management)

@ Scotiabank | Toronto, ON, CA, M5H1H1

Penetration Tester, Expert (Federal agency) - Tysons, VA - Full Time

@ iSoftTek Solutions | Tysons, Virginia, United States