Deepfake-Image Anti-Forensics with Adversarial Examples Attacks

Li Fan, Wei Li and Xiaohui Cui
Additional contact information
Li Fan: Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430040, China
Wei Li: School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214000, China
Xiaohui Cui: Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University, Wuhan 430040, China

Future Internet, 2021, vol. 13, issue 11, 1-14

Abstract: Many deepfake-image forensic detectors have been proposed and improved due to the development of synthetic techniques. However, recent studies show that most of these detectors are not immune to adversarial example attacks. Therefore, understanding the impact of adversarial examples on their performance is an important step towards improving deepfake-image detectors. This study developed an anti-forensics case study of two popular general deepfake detectors based on their accuracy and generalization. Herein, we propose the Poisson noise DeepFool (PNDF), an improved iterative adversarial examples generation method. This method can simply and effectively attack forensics detectors by adding perturbations to images in different directions. Our attacks can reduce its AUC from 0.9999 to 0.0331, and the detection accuracy of deepfake images from 0.9997 to 0.0731. Compared with state-of-the-art studies, our work provides an important defense direction for future research on deepfake-image detectors, by focusing on the generalization performance of detectors and their resistance to adversarial example attacks.

Keywords: adversarial examples; deepfake; general detectors; Poisson noise (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/13/11/288/pdf (application/pdf)
https://www.mdpi.com/1999-5903/13/11/288/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:13:y:2021:i:11:p:288-:d:681108

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().