Discriminating natural images and computer generated graphics based on the impact of CFA interpolation on the correlation of PRNU

Peng, Fei; Dongdong, Zhou

doi:10.1016/j.diin.2014.04.002

Cited by 21 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, since 3D face models are created from scratch with high fidelity texture data, these methods could not detect any forgery on spoofing media. On the other hand, new approaches (such as discrepancy analysis on color filter array of camera sensor noise or multi-fractal and regression analysis on discriminating natural and computer generated images) could be used as countermeasures against 3D-face-model-based attacks [33], [34]. However, attackers can extract genuine noise patterns or features from existing or captured images to embed them into generated video in a compromised device, thus, these defense mechanisms also fail against our threat model [35].…”

Section: B Compromising Attacks and Defensesmentioning

confidence: 99%

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Uzun¹

2018

Proceedings 2018 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Abstract-Facial/voice-based authentication is becoming increasingly popular (e.g., already adopted by MasterCard and AliPay), because it is easy to use. In particular, users can now authenticate themselves to online services by using their mobile phone to show themselves performing simple tasks like blinking or smiling in front of its built-in camera. Our study shows that many of the publicly available facial/voice recognition services (e.g. Microsoft Cognitive Services or Amazon Rekognition) are vulnerable to even the most primitive attacks. Furthermore, recent work on modeling a person's face/voice (e.g. Face2Face [1]) allows an adversary to create very authentic video/audio of any target victim to impersonate that target. All it takes to launch such attacks are a few pictures and voice samples of a victim, which can all be obtained by either abusing the camera and microphone of the victim's phone, or through the victim's social media account. In this work, we propose the Real Time Captcha (rtCaptcha) system, which stops/slows down such an attack by turning the adversary's task from creating authentic video/audio of the target victim performing known authentication tasks (e.g., smile, blink) to figuring out what is the authentication task, which is encoded as a Captcha. Specifically, when a user tries to authenticate using rtCaptcha, they will be presented a Captcha and will be asked to take a "selfie" video while announcing the answer to the Captcha. As such, the security guarantee of our system comes from the strength of Captcha, and not how well we can distinguish real faces/voices from synthesized ones. To demonstrate the usability and security of rtCaptcha, we conducted a user study to measure human response times to the most popular Captcha schemes. Our experiments show that, thanks to the humans' speed of solving Captchas, adversaries will have to solve Captchas in less than 2 seconds in order to appear live/human and defeat rtCaptcha, which is not possible for the best settings on the attack side.

show abstract

Section: B Compromising Attacks and Defensesmentioning

confidence: 99%

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Uzun¹

2018

Proceedings 2018 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

“…Dirik et al [8] focused on traces of demosaicing and chromatic aberration in color filter arrays (CFAs), as did Gallagher and Chen [12]. Peng et al [25] also targeted CFAs and identified the effect of their interpolation on the local correlation of photo response non-uniformity noise.…”

Section: Related Workmentioning

confidence: 99%

Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images

Nguyen

Tieu

Nguyen-Son

et al. 2018

Proceedings of the 13th International Conference on Availability, Reliability and Security

View full text Add to dashboard Cite

Discriminating between computer-generated images (CGIs) and photographic images (PIs) is not a new problem in digital image forensics. However, with advances in rendering techniques supported by strong hardware and in generative adversarial networks, CGIs are becoming indistinguishable from PIs in both human and computer perception. This means that malicious actors can use CGIs for spoofing facial authentication systems, impersonating other people, and creating fake news to be spread on social networks. The methods developed for discriminating between CGIs and PIs quickly become outdated and must be regularly enhanced to be able to reduce these attack surfaces. Leveraging recent advances in deep convolutional networks, we have built a modular CGI-PI discriminator with a customized VGG-19 network as the feature extractor, statistical convolutional neural networks as the feature transformers, and a discriminator. We also devised a probabilistic patch aggregation strategy to deal

show abstract

“…Recent development in computer graphics (CG) image rendering technology has made easy for the content creators to produce synthetic images which exhibits high photo-realism and hard to distinguish from photographic (PG) images by naked eyes. If such images are used illegitimately in journalism or forensic investigation, then it may cause serious threat to the society [1]. Therefore, classification of CG and PG images has become important research topic in the field of digital image forensics.…”

Section: Introductionmentioning

confidence: 99%

Classification of Computer Graphic Images and Photographic Images Based on Fusion of Color and Texture Features

Kumar¹,

Chennamma²

2021

RIA

View full text Add to dashboard Cite

With the rapid advancement in digital image rendering techniques, allows the user to create surrealistic computer graphic (CG) images which are hard to distinguish from photographs captured by digital cameras. In this paper, classification of CG images and photographic (PG) images based on fusion of global features is presented. Color and texture of an image represents global features. Texture feature descriptors such as gray level co-occurrence matrix (GLCM) and local binary pattern (LBP) are considered. Different combinations of these global features are investigated on various datasets. Experimental results show that, fusion of color and texture features subset can achieve best classification results over other feature combinations.

show abstract

Discriminating natural images and computer generated graphics based on the impact of CFA interpolation on the correlation of PRNU

Cited by 21 publications

References 7 publications

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Modular Convolutional Neural Network for Discriminating between Computer-Generated Images and Photographic Images

Classification of Computer Graphic Images and Photographic Images Based on Fusion of Color and Texture Features

Contact Info

Product

Resources

About