How phones could identify you by your grip

Your phone could one day stay safe from thieves by identifying you by your grip.

Researchers at Louisiana State University have found a way to use artificial intelligence (AI) to help phones analyze how users hold them. The method could help determine whether the phones are in the hands of their owners or someone else, according to a new study.

“AI has a strong ability to learn and identify a user’s biometric characteristics, especially when there aren’t many dedicated or high-fidelity sensors available on mobile phones,” the professor said. ‘computer science. Chen Wangone of the study’s authors, said in an interview.

Know thyself

Wang’s invention works when you pick up your phone. The phone’s microphone records sound when a notification tone plays. An AI-based algorithm processes sound and extracts biometric features to match the user’s feature profile or registered hand grip. If there is a match, the verification is successful and the notification preview is displayed on the screen. Otherwise, only the number of pending notifications is displayed.

Because people have different hand sizes, finger lengths, grip strengths and hand shapes, the impacts on sounds are different and can be learned and distinguished by AI, Wang said. Researchers call these body measurements and calculations related to human characteristics biometrics.

“AI provides a way to leverage readily available and inexpensive sensors on mobile devices, such as cameras, microphones, touchscreens and motion sensors, to identify a user,” he said. added. “In addition to traditional physiological biometrics, such as face, iris, and fingerprints, AI is also useful for extracting behavioral biometrics, including body movements, finger gestures, signatures, hand movements, voices and walking patterns, which are considered more difficult to reproduce by an opponent.

In an interview, Dan Simonthe vice president of AI and analytics at technology company Capgemini Americas said AI is useful in recognizing users because it can compensate for human weaknesses.

“In many cases, recognition is based on security codes or passwords to determine if something like a phone actually belongs to that particular person,” he added. “But the problem and limitation of using things like security questions is that they can be stolen or passwords can be forgotten by users. AI is useful as an alternative because it eliminates the risk of these limitations.

AI for recognition

You’ve probably come across AI identification before. Many forms of AI are used to recognize users, including facial recognition, voice recognition and fingerprints, Simion said. The technology is used to access cell phones and it could soon find its way into other gadgets like wearable devices, he added.

“For example, if the person’s heart rate is much higher than usual, or their activity level is much lower, the AI ​​can recognize these abnormalities because they don’t match the cognitive patterns of the normal owner. of the device.”

However, AI recognition still has its drawbacks. Wang said most AI-based user recognition methods still require the user to actively input biometric data. This will not work when user participation is not immediate, such as when the device is shared with friends or family members or when a message notification automatically appears on the locked screen .

Additionally, biometrics are prone to what researchers call replay attacks. For example, an adversary could physically fake the user’s face, fingerprint, and iris based on 3D printing, and AI can also be leveraged to digitally replicate the face, voice, and iris. other biometric data of the user.

According to Dave Maher, blockchain and secure computing expert and CTO of Intertrust, said in an interview, in the future, AI that follows patterns will be used to detect cyber threats. AI will increasingly be used to classify patterns of behavior to determine if those patterns represent nefarious behavior or to determine if a system is under attack.

One example is the Mirai botnet, which Maher likened to a mutant virus that infects IoT systems. The botnet can gather a large number of devices to attack the networks of which these devices are members.

“AI will be used to identify viruses and their mutant counterparts,” Maher said.

Another project Chen is working on could make your shopping safer. This system uses a hand holding the phone for verification at kiosks, such as the self-checkout at a grocery store.
When a user holds a phone near the kiosk for NFC or QR code authentication, the back of the user’s hand is captured by a camera on the booth.

“An AI-based method will process the gripping hand image and compare it to the user’s registered hand image by checking the shape of the gripping hand, skin patterns/colors and the grasping gesture,” Chen added.

Editors’ Recommendations