AuthenticID develops proprietary algorithms to mitigate biometric injection attacks

AuthenticID has introduced a software service designed to detect and combat deepfake and generative AI-based injection attacks against biometric verification systems. The software, developed by the company’s product and applied research team, utilizes proprietary algorithms to prevent AI-generated content from being used in fraudulent activities. This can be integrated into the company’s existing identity verification framework.

Alex Wong, vice president of product management at AuthenticID, underscored the significance of recent events and emphasized the need for advanced measures to authenticate user legitimacy. Wong cited a recent sophisticated deepfake scam in Hong Kong, in which a clerk was defrauded of $25 million by using deepfake to impersonate a company director.

“The widespread availability of inexpensive, easy-to-use tools allows bad actors to create highly convincing fake identity documents and biometric content,” Wong adds.

The software utilizes a combination of visual fraud algorithms, text fraud algorithms, and behavioral algorithms. According to the company, the entire system is automated, relying on machine learning to process and analyze data without human intervention. This automated nature of the system enables quick processing and the capability to detect and block injection and deepfake attacks within milliseconds, per the company’s statement.

AuthenticID emphasizes that one of the primary benefits of the software is its ability to remove human bias from the detection process. This ensures consistent and objective analysis. The claim of detecting fraud at the millisecond level means that potential fraud can be stopped in real time. The company was recently selected for an equity test as part of the GSA’s pilot of selfie biometrics for Login.gov.

“Traditional identity verification methods can’t keep up with both the sophistication and ease at which bad actors can circumvent security measures with the use of new tools. That’s why continuous innovation is necessary to meet fraudsters at the front line,” says Stephen Thwaits, senior vice president of global solutions at AuthenticID.

Article Topics

AuthenticID  |  biometric liveness detection  |  biometrics  |  deepfake detection  |  fraud prevention  |  generative AI  |  injection attack detection  |  research and development