Identity proofing and fraud detection company AuthenticID launched a new solution today to detect deep fake and generative AI injection attacks.
An injection attack occurs when a fraudster injects a deepfake– which could be a synthetic document, video, facial image, or audio representation– into an identity verification workflow to spoof the system. This works to bypass traditional fraud detection and identity verification methods.
The company noted that it uses three, proprietary algorithms to prevent the majority of digital injection attacks that leverage AI-generated content. The three algorithms include visual fraud algorithms that detect counterfeit and synthetic elements, text fraud algorithms that detect errors within false documents, and behavioral algorithms that focus on activity during the ID capture and submission.
AuthenticID’s automated approach limits human bias and lag time from interfering in the detection and decisioning process. This enables the new solution to stop injection attacks and deep fake attacks in a matter of milliseconds.
“The widespread availability of inexpensive, easy-to-use tools allows bad actors to create highly convincing fake identity documents and biometrics,” said AuthenticID VP Product Management Alex Wong. “Recent news stories have shown just how devastating these attacks can be to any organization. Our deep fake injection attack solution meets a critical need to determine the legitimacy of a user in this new era of technology.”
Despite the new technology’s level of sophistication, the company notes that its new algorithms are not a “silver bullet” to defend against injection attacks. That’s because fraudsters are perpetually evolving their tactics to circumvent new security methods.
Founded in 2001, AuthenticID offers identity proofing, ID verification, biometric authentication, and fraud shield tools to support the fight against cybercrime. Additionally, the company’s Identity Fraud Taskforce continuously develops new algorithms to improve AuthenticID’s identity decisioning engine to help identify and stop fraud.