Liveness Detection

Gelatin fingerprints, false irises, and special eyewear can readily deceive biometrics systems and their liveness detection capabilities in hollywood movies. Those deceptions aren’t going to fool today’s technology for a second. Biometric technology has grown demonstrably more accurate and immune to attacks thanks to AI and, more specifically, deep learning where a system can learn from data. Deep-fakes, bots, and advanced spoofing attacks have made certified liveness detection a must-have feature in any biometric-based verification solution.

What is Liveness Detection

In biometrics, liveness detection refers to a system’s capacity to determine whether a fingerprint, face, or other biometric is genuine (taken from a live individual present at the time of capture) or not (from a spoof artifact or lifeless body part). Biometric systems have been widely used around the world in response to the demand for accurate and secure authentication and authorization. Designing a biometric system that is resistant to existing and future spoof attacks is a major problem for the industry today. Fraudsters represent a wide range of hazards, all of which are extremely dangerous as they have access to cutting-edge technology such as resin 3D printers with a resolution of 25 microns and artificial intelligence. In essence, a liveness detection mechanism is a security feature designed to reduce the risk of spoofing attacks on biometric systems.

Facial Liveness Detection

Accuracy is no longer an issue when utilizing face biometrics for authentication. Spoofing attempts using printed photos, recordings, deep fake pictures, and 3D masks, on the other hand, pose a serious threat. Facial Liveness Detection incorporates specialized features to identify biometric spoofing attacks, which could be an imitation emulating a person’s unique biometrics scanned through the biometric detector to deceive or bypass the identification and authentication steps provided by the system. Even though face recognition can reliably answer the question, “Is this the right person?” but not the question, “Is this a live person?”, this is where liveness detection technology plays a significant role in fraud detection and mitigation. Face biometric matching must be able to detect spoofs in order to be trusted, as well as to maintain the integrity of our biometric data. In other words, liveness detection enables passive and active detection, so that our biometrics don’t have to be kept a secret, which is a good thing considering how many photos and videos we store and publish online.

Active Liveness detection

Users are required to respond to “challenges” such as head motions, smiling, and blinking, which takes time and effort. This method is more reliable and trustworthy than passive liveness, but we have seen a move from active solutions to today’s modern, passive liveness detection is being driven by the fact that firms are increasingly valuing user experience as a strategy to attract and keep customers. Active methods show better success.

Passive Liveness detection

Because the user is not required to take any action for the scanning process, there is less friction and user abandonment during procedures like remote customer onboarding. A passive liveness detection can be performed using a variety of methods, such as evaluating a selfie photograph, recording a video, or flashing lights on the person.

IDcentral’s Liveness detection solution

IDcentral integrates certified liveness detection AI that can detect and analyze liveness of a client from just a picture (Passive Detection) instantly. The solution is also trained to prevent recurrent vulnerabilities that less robust liveness technologies are susceptible to spoofing.

Features of IDcentral’s Liveness detection:

  • Passive Verification
  • Face Mapping/Face Trace Authentication
  • Ability to detect micro-movements-3D maping
  • Preference modes (Active/Passive) to improve customer fidelity
  • SDK based Integration
  • Highest accuracy rates in the industry (Overall Accuracy 90%+. FMR ~0.2%, FNMR <10%.)
  • Integrated AI intelligence for spoofing attacks against mobile video, paper masks, eye hole masks, latex masks

Know more about IDcentral’s Liveness detection feature

Request a Demo

Request a Demo