Researchers at Carnegie Mellon University and the University of North Carolina at Chapel Hill have developed a method of creating inconspicuous eyeglasses that can be used to thwart identification by facial recognition algorithms, according to their published findings (PDF). The researchers developed five pairs of “universal” glasses that “facilitate misclassification” through an adversarial generative nets (AGN) method, which involves using neural networks to produce designs with different colors and textures for glasses that can either evade correct identification or impersonate
A team of Google researchers has developed a way to defeat AI-based image recognition systems with adversarial images that can be printed at home, and do not need to be tuned to the image they are attempting to mask, The Verge reports. In a paper (PDF) describing their method for creating “universal, robust, targeted adversarial image patches in the real world,” the researchers say that prior work in the area has largely focussed on small or imperceptible changes to the
Researchers at Florida State University have developed a way for smartphones to read user’s lip gestures with sonar, enabling the gestures to be used as a liveness detection system to thwart replay attacks. The system, which the researchers call VoiceGesture, uses the phone’s speaker to transmit a high-frequency sound, which is reflected back to the microphone as the user says his or her password. It does not require and additional hardware, and can be integrated into existing smartphone operating systems
Researchers from the University of Eastern Finland have published a new study that reveals that it is relatively easy for skilled voice impersonators to dupe advanced voice recognition systems because they aren’t efficient in recognizing voice modifications, according to a report by V3. Though the majority of new mobile devices are integrated with built-in voice recognition and command capabilities, many of these systems fail to have adequate security mechanisms in place. As a result, these systems can be compromised by
Biometrics Institute CEO Isabelle Moeller recently penned an opinion-editorial emphasizing how stakeholders must balance the strengths and vulnerabilities of biometric technology, as its credibility relies on the industry’s efforts to collaborate globally. The recent rise of biometrics deployments in consumer services has confirmed spoofing as a vulnerability that needs careful management. Moeller states that the weaknesses in biometrics have “spawned a race between those creating and applying the solutions.” She adds that while all biometric systems have some flaws, what
Michigan State University biometrics expert Anil Jain and his team are developing a fake finger that possesses multiple key properties of human skin to determine how secure biometric recognition systems are, according to a report by MSU Today. Jain, a University Distinguished Professor, and doctoral student Joshua Engelsma have used the fake finger to test two of the most common types of fingerprint readers to help determine their resilience to spoof attacks. The team created the fake fingers using a
Precise Biometrics released a new whitepaper entitled “Spoof and Liveness Detection for the Mobile Biometrics Market”, which offers an introduction to spoof and liveness detection. Among the topics covered in the whitepaper are how a fingerprints spoof is done, current anti-spoofing solutions, and the standardization efforts taken to discover ways to evaluate spoof detection. According to Precise Biometrics, mobile payments is expected to be the next “killer application for biometrics and further accelerating the adoption.” The whitepaper forecasts that the
A new study by the University of Buffalo’s (UB) School of Engineering and Applied Sciences has found that voice-based smartphone apps such as Siri and WeChat can expose make you vulnerable to the growing security threat of voice hacking, according to a report on Phys.Org. Using only a few minutes of audio samples, attackers can replay your voice convincingly enough to trick people and advanced digital security systems to steal money from your bank account. A UB team of engineers
Researchers from the Chaos Computer Club (CCC) have successfully breached the Samsung Galaxy S8’s iris recognition system to unlock the device using an image of an iris, according to a report by Motherboard. CCC has posted a video demonstrating how they bypassed the iris scanner’s protections using a camera, a printer, and a contact lens. “We’ve had iris scanners that could be bypassed using a simple print-out,” said Linus Neumann, one of the CCC researchers who appears in the video.
HSBC’s voice ID authentication software designed to prevent bank fraud has been duped by BBC Click reporter Dan Simmons and his non-identical twin, according to a report by BBC News. Simmons created an HSBC account and signed up to the bank’s voice ID authentication service. His non-identical twin, Joe, was able to access the account via the telephone by impersonating his brother’s voice. HSBC said it would “review” ways to make the ID system more sensitive following the BBC investigation.