Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems

Ruiz, Nataniel; Bargal, Sarah Adel; Sclaroff, Stan

doi:10.1007/978-3-030-66823-5_14

Cited by 66 publications

(75 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This can be applied only in some contexts. Ruiz et al [72] proposed a method based on adversarial attacks as a defense. By adding a specific noise in the image, they are able to make that image unusable by a deepfake generator.…”

Section: Controlled Acquisition Devicementioning

confidence: 99%

Face Manipulation Detection in Remote Operational Systems

Pic

Mahfoudi

Trabelsi

et al. 2022

Handbook of Digital Face Manipulation and Detection

View full text Add to dashboard Cite

In this chapter, we present the various categories of Face Manipulation and their use within different remote operational systems. We then use the example of remote identity document onboarding systems to illustrate how each category can be used in practice to compromise such a system. After a definition of the different Face Manipulation categories and the common algorithms used to produce them, we go through the various manipulation detection algorithms and common image and video forgery datasets. We then introduce some known counter-forensics methods that can be used by an attacker to avoid detection. Knowing the detection methods and the counter-forensic, we present how we can build up a safer system by using the correct methods at the correct time. But also how knowledge about the tampering process could be used to design the user experience to make the systems harder to compromise. We complete this review by the standardisation effort and legal aspect on the matter. And we conclude by discussing the remaining challenges and perspectives for better use of nowadays detection methods in practical usage.

show abstract

Section: Controlled Acquisition Devicementioning

confidence: 99%

Face Manipulation Detection in Remote Operational Systems

Pic

Mahfoudi

Trabelsi

et al. 2022

Handbook of Digital Face Manipulation and Detection

View full text Add to dashboard Cite

show abstract

“…考虑到伪造检测算法 [72,87] 主要通过检测基于 GAN 模型生成人脸中特定的指纹特征来进行伪造图像的鉴别, Neves 等 [111] 提出移除这些指纹特征来欺骗现有的人脸伪造检测算法 [79] . Boston University 的 Ruiz 等 [112] 借鉴了传统的对抗样本攻击算法干扰伪造人脸图像的生成过程, 从而在生成结果中添加对抗扰动以实现攻击深度伪造算法的效果. Huang 等 [113] 提出可以通过对生成图像进行局部细节重建来消除其中的伪造线索, 从而达到欺骗现有伪造检测方法的目的.…”

Section: 面向对抗样本攻击的可信检测研究unclassified

Deep visual identity forgery and detection

彭春蕾¹,

高新波²,

王楠楠³

et al. 2021

Sci. Sin.-Inf.

View full text Add to dashboard Cite

With the wide application of deep learning techniques in video and image generation, the quality of visual identity forgery, especially face forgery, is becoming increasingly high. The detection of visual identity forgery has been a hot issue because of its important influence on both national security and social stability. In this paper, we introduce recent researches on deep visual identity forgery from target-specific face forgery and target-generic face forgery. We further summarize the techniques of detecting visual identity forgery from multiple categories, including the spatial clue based methods, the temporal clue based method, the techniques for generalizable forgery detection and spoofing forgery detection models. We later present the public datasets and performance of representative approaches on these datasets. Finally, the issues and challenges in existing research are discussed.

show abstract

“…Specifically, when the face image is uploaded to the Internet, there will be malicious behaviors such as Deepfake. [8] can effectively prevent malicious face change by using adversarial examples. However, the attack method based on gradient iteration requires huge storage space to load the substitution model.…”

Section: Introductionmentioning

confidence: 99%

Improving the Transferability of Adversarial Examples by Using Generative Adversarial Networks and Data Enhancement

Xie

Shi

Xie

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Deep neural networks (DNNs) can be attacked by adversarial examples that are undetectable by humans. Generation-based approaches have recently gained popularity because they directly translate the input distribution to the distribution of adversarial instances, making them more effective and efficient. However, existing techniques are susceptible to overfitting on the substitute model, limiting the transferability of adversarial examples. In this paper, we introduce data augmentation into AdvGAN, called AdvGAN-DE, which can dramatically improve the transferability of adversarial examples. Experiments demonstrate that we enhance the success rate by 31.09% for defense models and 10.23% for typically trained models on average when compared to AdvGAN.

show abstract

Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems

Cited by 66 publications

References 19 publications

Face Manipulation Detection in Remote Operational Systems

Face Manipulation Detection in Remote Operational Systems

Deep visual identity forgery and detection

Improving the Transferability of Adversarial Examples by Using Generative Adversarial Networks and Data Enhancement

Contact Info

Product

Resources

About