Zoloz enters the war on deepfakes with biometric detection software

Zoloz has released an update to its biometric deepfake detection software, which features upgraded defenses against evolving infiltration tactics, including AI face swapping attacks on facial recognition systems.

A press release from Zoloz – a subsidiary of Chinese conglomerate Ant Group that provides biometric identity verification – says its Zoloz Deeper product uses mobile sensor verification, multi-dimensional dynamic risk control and multimodal deep learning models to address AI security threats across system, application and server layers.

According to Pandaily, Zoloz Deeper’s algorithm is trained on 300,000 test samples generated using the GAN model, and is constantly undergoing offensive and defensive evaluations to keep on top of potential deepfake attack scenarios. It analyzes factors such as camera status, device and network conditions and input sources to ensure the authenticity and integrity of any biometric data it collects. And for liveness detection, it can assess facial micro-expressions, muscle textures and eye movements.

“Both the attacks and defenses with deepfake technologies are relative and constantly evolving processes,” says Tao Ye, product director of Zoloz. “As we advance, so does deepfake technology. What we need to do is stay ahead of it.”

In tandem with the launch, Zoloz is collaborating with the Ant Group Security Response Center to establish a multi-million dollar prize pool for security hobbyists who discover vulnerabilities in Zoloz Deeper and report them through a web portal.

Zoloz’s cloud-based, automated eKYC and ID verification tools are used by banks in Indonesia, the Philippines and elsewhere in Asia. In November of 2023, it reported a 300 percent increase in international business operations over the preceding year.

Article Topics

Ant Group  |  biometric liveness detection  |  biometrics  |  deepfake detection  |  face swap  |  Zoloz  |  Zoloz Deeper