Face liveness detection using variable focusing

Kim, Soo-Yeon; Yu, Sunjin; Kim, K.; Ban, Yoojin; Lee, Sangyoun

doi:10.1109/icb.2013.6613002

Cited by 49 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, we tested the Captcha used in our study against one of the OCR-based Captcha solving websites 15 . As presented in the Attack ocr columns of Table III, the tested site could not solve any of our Captcha challenges.…”

Section: B Automated Attacks Under T H Legit = 5secmentioning

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 Automated Attacks Under T H Legit = 5secmentioning

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

“…In this paper, we revise the model considering the blurriness proposed in [10]. Differently, the photos are focused on the face and the background rather than the ear and the nose in order to increase the differences of the blurriness.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…And each photo and video replay is measured at different distances to form the database. The blurriness of two images which is focused on the nose and the ear separately is analyzed to determine whether the object is 3D [10].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Face liveness detection by focusing on frontal faces and image backgrounds

Liu

2014

2014 International Conference on Wavelet Analysis and Pattern Recognition

View full text Add to dashboard Cite

Face recognition systems have been deployed in many security applications nowadays. Its popularity attracts the attention of an adversary. One of the common methods is to show a photo or video in front of the camera to mislead the detection of the system. In this paper, we propose a face liveness detection method by investigating the focus distance between the face and the background. The focus distance should be the same for the photo or video, while the distance should be different for a real person. The experimental results illustrate that the performance of the detection is improved significantly by using our method in comparison with the one considering the focus distance between the nose and the ear.

show abstract

“…The calibration process must be repeated if the camera resolution changes [32], and consists of the following six steps:…”

Section: Design Of the Android Mobile Applicationmentioning

confidence: 99%

Access Control in Smart Homes by Android-Based Liveness Detection

Spinsante¹,

Montanini²,

Bartolucci³

et al. 2017

ICST Transactions on Ambient Systems

View full text Add to dashboard Cite

Technologies for personal safety and security play an increasing role in modern life, and are among the most valuable features expected to be supported by so-called smart homes. This paper presents a low-complexity Android application designed for both mobile and embedded devices, that exploits the available on-board camera to easily capture two images of a subject, and processes them to discriminate a true 3D and live face, from a fake or printed 2D one. The liveness detection based on such a discrimination provides antispoofing capabilities to secure access control based on face recognition. The limited computational complexity of the developed application makes it suitable for practical implementation in video-entry phones based on embedded Android platforms. The results obtained are satisfactory even in different ambient light conditions, and further improvements are being developed to deal with low precision image acquisition.

show abstract

Face liveness detection using variable focusing

Cited by 49 publications

References 17 publications

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Face liveness detection by focusing on frontal faces and image backgrounds

Access Control in Smart Homes by Android-Based Liveness Detection

Contact Info

Product

Resources

About