Legal Knowledge Management and the Rise of Artificial Intelligence
Robotic Refactoring the Workplace
Why Your Next Insurance Claims Processor Could be a Robot
The Forgotten Element in Your Big Data Strategy
"AI -The Future of Automotive Industry"
Nitin Sethi, Global IT Director - Business Transformation & Engagement, Visteon Corporation
WiFi Networks: Shifting from Providing a Service to Improving the...
Daniel J. Strojny, Interim Associate Director of Network and IT Operations, University of St. Thomas
Breaking the Stereotypes in the Development of AI
Yves Jacquier, Executive Director, Production Studio Services, Ubisoft
Operationalize Machine Learning
Zongjie Diao, Director of Product Strategy and Management, Data Center Compute Group, CISCO
Thank you for Subscribing to CIO Applications Weekly Brief
The New Age of Behavior-based Security
Almost every smartphone company believes in the fingerprint-based authentication system. Not only the mobile manufacturers but also banks like Wells Fargo and HSBC rely on this security system. But, the DeepMasterPrints experiment has revealed how the proper use of Artificial Intelligence can make this system vulnerable.
The fingerprint-based systems never use the total fingerprint of a person. It uses only a part. These partial fingerprints are not as unique as a full fingerprint. MasterPrint is used to make a synthetic fingerprint that can replace the original one. These digitally altered images can befool the fingerprint security system easily. Failure of the password as a security tool led to the manufacturers using the fingerprint capability. A report by Forrester said that 81 percent of total data breaches happened due to the failure of the password.
A naked eye can quickly identify the image of a partial fingerprint, but it is not possible for the current fingerprint software to determine it. The MasterPrints are more successful than the real ones. It uses an important technology that is called Generative Adversarial Networks or GAN. GAN is used to create ‘deepfakes’ videos. This GAN technology can also deceive the image-recognition technology. A pair of neural networks and GANs work together, and this combination creates realistic images that can destroy the image-recognition system.
The researchers used artificial and realistic images to test the fingerprint sensors. They easily threw dust in the eyes of commercial sensors. This research broke fingerprint security of almost 65 percent of phones. To meet this problem, Behavioral biometrics has a vital role play. Behavioral biometrics works using the activity of the user. It does not rely on the fingerprint or face recognition system. Companies such as UnifyID, SecureAuth, and BehavioSec are already using this technology for safety.
Despite these failures, fingerprint security can be improved using different methods. The companies should focus on increasing the security level. They need to upgrade their security with the changing time. Undoubtedly, behavioral security is futuristic. It is popular in the e-commerce, financial, healthcare and travel sectors. The health insurance company Aetna has already started to use behavior-based security service for better customer experience.