rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Uzun, Erkam

doi:10.14722/ndss.2018.23253

Cited by 37 publications

(22 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) The paper had to propose an authentication scheme. Specifically, the paper had to use machine learning to label [12], [33], [41], [42] IMWUT/UbiComp [11], [20], [25], [35], [48] INFOCOM [8], [36], [45], [51], [53] MobiCom [15], [32] MobiSys [7], [31] NDSS [5], [17], [49], [50] Pattern Recognition [2], [9], [18], [24], [38], [40], [54]…”

Section: Review Of Recent Authentication Systemsmentioning

confidence: 99%

Robust Performance Metrics for Authentication Systems

Sugrim

Liu

McLean³

et al. 2019

Proceedings 2019 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Research has produced many types of authentication systems that use machine learning. However, there is no consistent approach for reporting performance metrics and the reported metrics are inadequate. In this work, we show that several of the common metrics used for reporting performance, such as maximum accuracy (ACC), equal error rate (EER) and area under the ROC curve (AUROC), are inherently flawed. These common metrics hide the details of the inherent tradeoffs a system must make when implemented. Our findings show that current metrics give no insight into how system performance degrades outside the ideal conditions in which they were designed. We argue that adequate performance reporting must be provided to enable meaningful evaluation and that current, commonly used approaches fail in this regard. We present the unnormalized frequency count of scores (FCS) to demonstrate the mathematical underpinnings that lead to these failures and show how they can be avoided. The FCS can be used to augment the performance reporting to enable comparison across systems in a visual way. When reported with the Receiver Operating Characteristics curve (ROC), these two metrics provide a solution to the limitations of currently reported metrics. Finally, we show how to use the FCS and ROC metrics to evaluate and compare different authentication systems.

show abstract

Section: Review Of Recent Authentication Systemsmentioning

confidence: 99%

Robust Performance Metrics for Authentication Systems

Sugrim

Liu

McLean³

et al. 2019

Proceedings 2019 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

show abstract

“…Computer vision and machine learning techniques have advanced to a stage that makes existing schemes for the automated distinction of human users from bots seem fruitless. Much recent work focuses on various authentication methods, e.g., photo-based authentication schemes [33] and liveness detection-based authentication [24] . Motivated by Uzun et al [24] , who proposed a liveness detection captcha system called rtCaptcha, another future work direction is to design a robust captcha scheme based on voice authentication, video authentication, etc.…”

Section: Discussionmentioning

confidence: 99%

“…Kim et al [23] proposed Age-CAPTCHA, a captcha scheme that requires a user to annotate images of human faces with their age group. Based on facial authentication, Uzum et al [24] proposed the real time Captcha (rtCaptcha) system, which requires a user to perform a known authentic video or visual act (e.g., smile or blink) to figure out the captcha solution.…”

Section: Background and Related Work 21 Threat Modelmentioning

confidence: 99%

Towards understanding the security of modern image captchas and underground captcha-solving services

Weng

Zhao

et al. 2019

Big Data Min. Anal.

View full text Add to dashboard Cite

Image captchas have recently become very popular and are widely deployed across the Internet to defend against abusive programs. However, the ever-advancing capabilities of computer vision have gradually diminished the security of image captchas and made them vulnerable to attack. In this paper, we first classify the currently popular image captchas into three categories: selection-based captchas, slide-based captchas, and click-based captchas. Second, we propose simple yet powerful attack frameworks against each of these categories of image captchas. Third, we systematically evaluate our attack frameworks against 10 popular real-world image captchas, including captchas from tencent.com, google.com, and 12306.cn. Fourth, we compare our attacks against nine online image recognition services and against human labors from eight underground captcha-solving services. Our evaluation results show that (1) each of the popular image captchas that we study is vulnerable to our attacks; (2) our attacks yield the highest captcha-breaking success rate compared with state-of-the-art methods in almost all scenarios; and (3) our attacks achieve almost as high a success rate as human labor while being much faster. Based on our evaluation, we identify some design flaws in these popular schemes, along with some best practices and design principles for more secure captchas. We also examine the underground market for captcha-solving services, identifying 152 such services. We then seek to measure this underground market with data from these services. Our findings shed light on understanding the scale, impact, and commercial landscape of the underground market for captcha solving.

show abstract

“…User cooperation-based techniques look for presentation attacks by exclusively initiating a secondary interaction between the user and the detection module [14]. One such example is prompting the user to perform a certain movement or action.…”

Section: Related Workmentioning

confidence: 99%

Live Spoofing Detection for Automatic Human Activity Recognition Applications

Huszár

Adhikarla²

2021

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) has become increasingly crucial in several applications, ranging from motion-driven virtual games to automated video surveillance systems. In these applications, sensors such as smart phone cameras, web cameras or CCTV cameras are used for detecting and tracking physical activities of users. Inevitably, spoof detection in HAR is essential to prevent anomalies and false alarms. To this end, we propose a deep learning based approach that can be used to detect spoofing in various fields such as border control, institutional security and public safety by surveillance cameras. Specifically, in this work, we address the problem of detecting spoofing occurring from video replay attacks, which is more common in such applications. We present a new database containing several videos of users juggling a football, captured under different lighting conditions and using different display and capture devices. We train our models using this database and the proposed system is capable of running in parallel with the HAR algorithms in real-time. Our experimental results show that our approach precisely detects video replay spoofing attacks and generalizes well, even to other applications such as spoof detection in face biometric authentication. Results show that our approach is effective even under resizing and compression artifacts that are common in HAR applications using remote server connections.

show abstract

rtCaptcha: A Real-Time CAPTCHA Based Liveness Detection System

Cited by 37 publications

References 43 publications

Robust Performance Metrics for Authentication Systems

Robust Performance Metrics for Authentication Systems

Towards understanding the security of modern image captchas and underground captcha-solving services

Live Spoofing Detection for Automatic Human Activity Recognition Applications

Contact Info

Product

Resources

About