HomeRegionalAMAThales’s Friendly Hackers unit invents metamodel to detect AI-generated deepfake images

Thales’s Friendly Hackers unit invents metamodel to detect AI-generated deepfake images

  • As part of the challenge organised by France’s Defence Innovation Agency (AID) to detect images created by today’s AI platforms, the teams at cortAIx, Thales’s AI accelerator, have developed a metamodel capable of detecting AI-generated deepfakes.
  • The Thales metamodel is built on an aggregation of models, each of which assigns an authenticity score to an image to determine whether it is real or fake.
  • Artificially generated AI image, video and audio content is increasingly being used for the purposes of disinformation, manipulation and identity fraud.

MEUDON, France, 22 November 2024 -/African Media Agency(AMA)/- Artificial intelligence is the central theme of this year’s European Cyber Week from 19-21 November in Rennes, Brittany. In a challenge organised to coincide with the event by France’s Defence Innovation Agency (AID), Thales teams have successfully developed a metamodel for detecting AI-generated images. As the use of AI technologies gains traction, and at a time when disinformation is becoming increasingly prevalent in the media and impacting every sector of the economy, the deepfake detection metamodel offers a way to combat image manipulation in a wide range of use cases, such as the fight against identity fraud.

AI-generated images are created using AI platforms such as Midjourney, Dall-E and Firefly. Some studies have predicted that within a few years the use of deepfakes for identity theft and fraud could cause huge financial losses. Gartner has estimated that around 20% of cyberattacks in 2023 likely included deepfake content as part of disinformation and manipulation campaigns. Their report highlights the growing use of deepfakes in financial fraud and advanced phishing attacks.

Thales’s deepfake detection metamodel addresses the problem of identity fraud and morphing techniques,” said Christophe MeyerSenior Expert in AI and CTO of cortAIxThales’s AI accelerator. “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. This is a remarkable technological advance and a testament to the expertise of Thales’s AI researchers.

The Thales metamodel uses machine learning techniques, decision trees and evaluations of the strengths and weaknesses of each model to analyse the authenticity of an image. It combines various models, including:

  • The CLIP method (Contrastive Language-Image Pre-training) involves connecting image and text by learning common representations. To detect deepfakes, the CLIP method analyses images and compares them with their textual descriptions to identify inconsistencies and visual artefacts.
  • The DNF (Diffusion Noise Feature) method uses current image-generation architectures (called diffusion models) to detect deepfakes. Diffusion models are based on an estimate of the amount of noise to be added to an image to cause a “hallucination”, which creates content out of nothing, and this estimate can be used in turn to detect whether an image has been generated by AI.
  • The DCT (Discrete Cosine Transform) method of deepfake detection analyses the spatial frequencies of an image to spot hidden artefacts. By transforming an image from the spatial domain (pixels) to the frequency domain, DCT can detect subtle anomalies in the image structure, which occur when deepfakes are generated and are often invisible to the naked eye.

The Thales team behind the invention is part of cortAIx, the Group’s AI accelerator, which has over 600 AI researchers and engineers, 150 of whom are based at the Saclay research and technology cluster south of Paris and work on mission-critical systems. The Friendly Hackers team has developed a toolbox called BattleBox to help assess the robustness of AI-enabled systems against attacks designed to exploit the intrinsic vulnerabilities of different AI models (including Large Language Models), such as adversarial attacks and attempts to extract sensitive information. To counter these attacks, the team develops advanced countermeasures such as unlearning, federated learning, model watermarking and model hardening.

In 2023, Thales demonstrated its expertise during the CAID challenge (Conference on Artificial Intelligence for Defence) organised by the French defence procurement agency (DGA), which involved finding AI training data even after it had been deleted from the system to protect confidentiality.

Distributed by African Media Agency (AMA) on behalf of Thales.

About Thales
Thales (Euronext Paris: HO) is a global leader in advanced technologies specialising in three business domains: Defence & Security, Aeronautics & Space and Cybersecurity & Digital Identity.
The Group develops products and solutions that help make the world safer, greener and more inclusive.
Thales invests close to €4 billion a year in Research & Development, particularly in key innovation areas such as IA, cybersecurity, quantum technologies, cloud technologies and 6G.
Thales has 81,000 employees in 68 countries. In 2023, the Group generated sales of €18.4 billion.

PRESS CONTACT
Thales, Media relations
pressroom@thalesgroup.com

The post Thales’s Friendly Hackers unit invents metamodel to detect AI-generated deepfake images appeared first on African Media Agency.

Source : African Media Agency (AMA)

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.

- Advertisment -

Most Popular

Recent Comments

Sylvester Movette zunda on Mali wedding attack kills 21
James Hastings Chidule on Malawi’ fistula recovery at 86%
WELLINGTON WITMAN MOSELIJAH LUNDUKA on The history of Ngoni Maseko in Malawi
Lisa Frank on Home
azw3 on Home
Define Regtech on Home
Tobias Kunkumbira on Malawi to roll out Typhoid vaccine
arena plus nba standings 2022 to 2023 ph on Home
David on Home
마산출장 on Home
Cristina Thomas on Home
Alicia Alvarado on Home
The History of online Casinos – Agora Poker – hao029 on The History of online Casinos
Five factors that will determine #NigeriaDecides2023 - NEWSCABAL on Leadership Is Difficult Because Governance Is Very Stubborn, By Owei Lakemfa
Asal Usul Texas Holdem Poker – Agora Poker – hao029 on The Origins of Texas Holdem Poker
Malawi has asked Mike Tyson to be its cannabis ambassador - Techio on Malawi lawmaker Chomanika against Mike Tyson’s appointment as Cannabis Brand Ambassador over sex offence
Finley Mbella on Brand Chakwera leaks Part 1
Maria Eduarda Bernardo on The 2021 Guide to Trading Forex Online
Atsogo Kemso, Political Foot Soldier on Why MCP and UTM Alliance Will Fail
Em. Prof. Willem Van Cotthem - Ghent University, Belgium on Malawi army, National bank cover Chilumba barrack with trees
Christopher Murdock on Why dating older woman is dangerous?
Samantha The Hammer on Why dating older woman is dangerous?