Google improves smile recognition algorithm accuracy with demographic classifiers

Google researchers have discovered a way to improve the company’s smile detection algorithms across genders and races, which reaches a state-of-the-art 91 percent on the Faces of the World dataset, according to a research paper published on arXive (PDF). Technology Review reports that this represents a 1.5 percent improvement over the previous best accuracy. The researchers used four racial and two gender classifications to improve accuracy while preserving privacy, according to the paper. Their method involves utilizing transfer learning and

Scientists developing thumb-based continuous authentication solution for smartphones

The National Science Foundation (NSF) has awarded a team of researchers with a $718,000 grant to develop a thumb-based continuous authentication system that could be integrated into smartphones to detect unauthorized access, according to Illinois State University News. The team will include Jianwei La, an assistant professor at Illinois State University’s School of Information Technology. The NSF’s Division of Computer and Network Systems grant will help in developing an authentication process, which can also be used by individuals with visual

Researchers using wearables to increase voice authentication security

Researchers at the University of Michigan have developed new technique that allows wearables — such as a security-token necklace, ear buds or eyeglasses — to be used to eliminate vulnerabilities in voice authentication, according to a report by Phys.org. Researchers call sound an “open channel” that can be easily duplicated by novice impersonators and skilled hackers alike. “Increasingly, voice is being used as a security feature but it actually has huge holes in it,” said Kang Shin, the Kevin and

Authentication system for wearables combines behavioral biometrics with voice recognition

Researchers from the College of William and Mary have published a first-of-its-kind study that reveals that combining voice and touch recognition may help to prevent hackers from accessing personal data, according to a report by IEEE Xplore. The researchers claim to be the first to combine behavioral biometrics from different dimensions, which includes touch gestures, with voice commands for use with wearable glasses. The study explores the development of a new continuous authentication system for increased privacy protection could make

EAB awards young researchers for outstanding work in the area of biometrics

The European Association for Biometrics (EAB) recently acknowledged three young researchers for outstanding works in the area of biometrics. Award applicants were asked to submit a research paper and supporting information from which an international jury selected the candidates to present their significant contribution in front of the jury, the EAB members and the public audience. These awards are granted annually to individuals who have been judged by a panel of internationally respected experts to be making a significant contribution

UB researchers have developed heart scan authentication system

A University of Buffalo-led research team has developed a contactless authentication system that can scan the dimensions of a user’s heart as an identifier to authenticate devices. “Logging-in and logging-out are tedious,” said Wenyao Xu, assistant professor at the University of Buffalo’s department of computer science and engineering and the lead author of “Cardiac Scan: A Non-Contact and Continuous Heart-Based User Authentication System”, a paper to be presented next month at MobiCom. Xu added that the system would be the

Biometrics Institute names Stephanie Schuckers head of Academic Research and Innovation Group

The Biometrics Institute has introduced Stephanie Schuckers as the new Head of the Institute’s Academic Research and Innovation Group, a committee within the Biometrics Institute set up to further strengthen its outreach into the research community. Schuckers is a Clarkson University professor and Director of the Center of Identification Technology Research (CITeR), a National Science Foundation Industry/University Cooperative Research Center. She has testified for Congress, and has over 40 journal publications as well as over 60 other academic publications. The

Idiap study explores impact of score fusion on voice biometrics, presentation attack detection

Researchers at Idiap Research Institute Biometrics Group in Switzerland have conducted an extensive study of eight presentation attack detection (PAD methods) in which they assessed their ability to detect known and unknown attacks using publically available speaker databases with spoofing attacks, AVspoof and ASVspoof. Authored by research associate Pavel Korshunov and senior researcher Sébastien Marcel, the study is published in the latest issue of IEEE Journal of Selected Topics in Signal Processing. Automatic speaker verification (ASV) systems are highly vulnerable

Researchers develop quantum biometrics technique to identify people

Researchers at National Technical University of Athens in Greece have developed a way to exploit quantum mechanics to securely identify individuals, according to a report by Technology Review. Michail Loulakis and his team say that quantum biometrics makes identification more accurate and harder for fraudsters to exploit to gain unauthorized access. Based on the principle that the human eye can detect single photons, the new technique involves special light-detection equipment that relies on rhodopsin molecules in retinal rod cells to

Researchers find smartphone fingerprint sensors potentially vulnerable to “MasterPrints”

Smartphone fingerprint sensors could be fooled up to 65 percent of the time by “MasterPrints” digitally composed from common fingerprint features, according to findings published Monday by researchers at New York University and Michigan State University. In the report MasterPrint: Exploring the Vulnerability of Partial Fingerprint-based Authentication Systems, the researchers warn that partial fingerprint-based authentication systems are potentially vulnerable to compromise, particularly when multiple impressions of each finger are enrolled. Enrolling multiple impressions is often required by devices to ensure