Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector

Nguyen, Huy H.; Tieu, Ngoc-Dung T.; Nguyen-Son, Hoang-Quoe; Yamagishi, Junichi; Echizen, Isao

doi:10.1109/icme.2018.8486579

Cited by 7 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From a reconstruction perspective, Nguyen et al [32] proposed a method to fool detectors by transforming computer-generated images into new images with encoding features of natural images. Peng et al [33] proposed a new generative adversarial network architecture, CGR-GAN, to resolve the problem of insufficient color, lack of texture details, and light changes of the work [32]. Peng et al [34] subsequently proposed the BDC-GAN structure to realize bidirectional conversion between natural and computer-generated images.…”

Section: B Image Anti-forensicsmentioning

confidence: 99%

A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics

Zhang

Chen

Wang

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Although the current generative adversarial networks (GAN)-generated face forensic detectors based on deep neural networks (DNNs) have achieved considerable performance, they are vulnerable to adversarial attacks. In this paper, an effective local perturbation generation method is proposed to expose the vulnerability of state-of-the-art forensic detectors. The main idea is to mine the fake faces' areas of common concern in multiple-detectors' decision-making, then generate local anti-forensic perturbations by GANs in these areas to enhance the visual quality and transferability of anti-forensic faces. Meanwhile, in order to improve the anti-forensic effect, a doublemask (soft mask and hard mask) strategy and a three-part loss (the GAN training loss, the adversarial loss consisting of ensemble classification loss and ensemble feature loss, and the regularization loss) are designed for the training of the generator. Experiments conducted on fake faces generated by StyleGAN demonstrate the proposed method's advantage over the state-of-the-art methods in terms of anti-forensic success rate, imperceptibility, and transferability. The source code is available at https://github.com/imagecbj/A-Local-Perturbation-Generation-Method-for-GAN-generated-Face-Anti-forensics.

show abstract

Section: B Image Anti-forensicsmentioning

confidence: 99%

A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics

Zhang

Chen

Wang

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

show abstract

“…Detector [47] A presentation attack is commonly used to bypass authentication systems using biometrics information (face, fingerprint, iris, and/or voice). Integration of a natural-CG image/video discriminator into the system before the authentication phase is one approach to preventing such attacks.…”

Section: Face Enhancement To Avoid Detection By Spoofingmentioning

confidence: 99%

“…We developed a method for avoiding detection by those such detectors like those mentioned above [47]. It works Table 1 Accuracy and detection rate before and after applying our proposed method on a custom database with images selected from MIT [52] and MS-Celeb database [53].…”

Section: Face Enhancement To Avoid Detection By Spoofingmentioning

confidence: 99%

Generation and Detection of Media Clones

Echizen

Babaguchi

Yamagishi

et al. 2021

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

“…Nguyen et al reported an attack method that transforms computer-generated (CG) images into natural images before feeding them into a facial authentication system [24]. The transformation model is trained using a generative adversarial network (GAN) [25].…”

Section: Related Workmentioning

confidence: 99%

Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems

Fang

Yamagishi

Echizen

et al. 2018

2018 IEEE International Workshop on Information Forensics and Security (WIFS)

Self Cite

View full text Add to dashboard Cite

Automatic speaker verification (ASV) systems use a playback detector to filter out playback attacks and ensure verification reliability. Since current playback detection models are almost always trained using genuine and playedback speech, it may be possible to degrade their performance by transforming the acoustic characteristics of the played-back speech close to that of the genuine speech. One way to do this is to enhance speech "stolen" from the target speaker before playback. We tested the effectiveness of a playback attack using this method by using the speech enhancement generative adversarial network to transform acoustic characteristics. Experimental results showed that use of this "enhanced stolen speech" method significantly increases the equal error rates for the baseline used in the ASVspoof 2017 challenge and for a light convolutional neural network-based method. The results also showed that its use degrades the performance of a Gaussian mixture modeluniversal background model-based ASV system. This type of attack is thus an urgent problem needing to be solved.

show abstract

Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector

Cited by 7 publications

References 13 publications

A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics

A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics

Generation and Detection of Media Clones

Transforming acoustic characteristics to deceive playback spoofing countermeasures of speaker verification systems

Contact Info

Product

Resources

About