A French advanced technologies company has developed a program to detect AI-generated deepfakes.
Thales, which operates in more than 50 countries, including Australia, is heavily involved in the Defence, Aerospace and Cybersecurity sectors.
The company’s Senior Export in Artificial Intelligence (AI) Christophe Meyer said the new metamodel was built on an aggregation of models, each of which assigned an authenticity score to an image to determine whether it was real or fake.
Mr Meyer said artificially generated AI images, videos and audio content were increasingly being used for the purposes of disinformation, manipulation and identity fraud.
“Thales’s deepfake detection metamodel addresses the problem of identity fraud and morphing techniques,” he said.
“Aggregating multiple methods using neural networks, noise detection and spatial frequency analysis helps us better protect the growing number of solutions requiring biometric identity checks.”
Mr Meyer said Thales’ metamodel used machine learning techniques, decision trees and evaluations of the strengths and weaknesses of each model to analyse the authenticity of an image.
He said it was developed in response to a challenge organised by France’s Defence Innovation Agency.
