Security of Facial Forensics Models Against Adversarial Attacks

Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether they are secure against adversarial attacks. We experimentally demonstrated the existence of individual adversarial per...

Full description

Saved in:
Bibliographic Details
Main Authors: Huang, Rong, Fang, Fuming, Nguyen, Huy H., Yamagishi, Junichi, Echizen, Isao
Format: Conference Proceeding
Language:English
Subjects:
adversarial attack
Forensics
Forgery
forgery forensics
Image segmentation
Linear programming
Neurons
over-firing
Perturbation methods
Security
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep neural networks (DNNs) have been used in digital forensics to identify fake facial images. We investigated several DNN-based forgery forensics models (FFMs) to examine whether they are secure against adversarial attacks. We experimentally demonstrated the existence of individual adversarial perturbations (IAPs) and universal adversarial perturbations (UAPs) that can lead a well-performed FFM to misbehave. Based on iterative procedure, gradient information is used to generate two kinds of IAPs that can be used to fabricate classification and segmentation outputs. In contrast, UAPs are generated on the basis of over-firing. We designed a new objective function that encourages neurons to over-fire, which makes UAP generation feasible even without using training data. Experiments demonstrated the transferability of UAPs across unseen datasets and unseen FFMs. Moreover, we conducted subjective assessment for imperceptibility of the adversarial perturbations, revealing that the crafted UAPs are visually negligible. These findings provide a baseline for evaluating the adversarial security of FFMs.
ISSN:2381-8549
DOI:10.1109/ICIP40778.2020.9190678