Evading Deepfake-Image Detectors with White- and Black-Box Attacks

Carlini, Nicholas; Farid, Hany

doi:10.1109/cvprw50498.2020.00337

Cited by 132 publications

(97 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the popular attack methods such as FGSM [12] and PGD [13], use the gradient information of the model for the input images to generate perturbations which can be misclassified by detectors. Farid et al [14] also proposed that the forensic models could be invalidated by adversarial examples, which verified the unreliability of detectors. But since the structure of forensic models being unknown, these methods find a substitution model to perform their attack.…”

Section: Introductionmentioning

confidence: 94%

Adversarial Attack on Fake-Faces Detectors Under White and Black Box Scenarios

Wang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Generative Adversarial Network (GAN) models have been widely used in various fields. More recently, styleGAN and styleGAN2 have been developed to synthesize faces that are indistinguishable to the human eyes, which could pose a threat to public security. But latest work has shown that it is possible to identify fakes using powerful CNN networks as classifiers. However, the reliability of these techniques is unknown. Therefore, in this paper we focus on the generation of contentpreserving images from fake faces to spoof classifiers. Two GAN-based frameworks are proposed to achieve the goal in the white-box and black-box. For the white-box, a network without up/down sampling is proposed to generate face images to confuse the classifier. In the black-box scenario (where the classifier is unknown), real data is introduced as a guidance for GAN structure to make it adversarial, and a Real Extractor as an auxiliary network to constrain the feature distance between the generated images and the real data to enhance the adversarial capability. Experimental results show that the proposed method effectively reduces the detection accuracy of forensic models with good transferability.

show abstract

Section: Introductionmentioning

confidence: 94%

Adversarial Attack on Fake-Faces Detectors Under White and Black Box Scenarios

Wang

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

“…In the field of deepfake detection, neural networks are widely used to distinguish forgery videos. However, due to inherent defects, neural networks cannot resist attacks of adversarial samples [86][87][88]. To this end, researchers need to design more robust algorithms that can In recent years, deepfake technologies, which rely on deep learning, are developing at an unprecedented rate.…”

Section: Antiforensicsmentioning

confidence: 99%

A Survey on Deepfake Video Detection

Xia

Fei

et al. 2021

IET Biometrics

View full text Add to dashboard Cite

Recently, deepfake videos, generated by deep learning algorithms, have attracted widespread attention. Deepfake technology can be used to perform face manipulation with high realism. So far, there have been a large amount of deepfake videos circulating on the Internet, most of which target at celebrities or politicians. These videos are often used to damage the reputation of celebrities and guide public opinion, greatly threatening social stability. Although the deepfake algorithm itself has no attributes of good or evil, this technology has been widely used for negative purposes. To prevent it from threatening human society, a series of research have been launched, including developing detection methods and building large-scale benchmarks. This review aims to demonstrate the current research status of deepfake video detection, especially, generation process, several detection methods and existing benchmarks. It has been revealed that current detection methods are still insufficient to be applied in real scenes, and further research should pay more attention to the generalization and robustness.This is an open access article under the terms of the Creative Commons Attribution-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited and no modifications or adaptations are made.

show abstract

“…The majority of GAN-synthesized image detection methods are based on extracting signal level cues then train classifiers such as SVMs or deep neural networks to distinguish them from real images. Although high performance has been reported using these methods, they also suffer from some common drawbacks, including the lack of interpretability of the detection results, low robustness to laundering operations and adversarial attacks [11], and poor generalization across different synthesis methods. A different type of detection methods takes advantage Fig.…”

Section: Introductionmentioning

confidence: 99%

Exposing GAN-Generated Faces Using Inconsistent Corneal Specular Highlights

Lyu

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces.

show abstract

Evading Deepfake-Image Detectors with White- and Black-Box Attacks

Cited by 132 publications

References 14 publications

Adversarial Attack on Fake-Faces Detectors Under White and Black Box Scenarios

Adversarial Attack on Fake-Faces Detectors Under White and Black Box Scenarios

A Survey on Deepfake Video Detection

Exposing GAN-Generated Faces Using Inconsistent Corneal Specular Highlights

Contact Info

Product

Resources

About