After winning the 2023 edition of the Challenge organized by the AID (Defence Innovation Agency), the Friendly Hackers team from Thales stands out once again in 2024, thanks to particularly ingenious technology, a metamodel for detecting images generated by AI (deepfakes).
The Thales metamodel is built on an aggregation of models, each assigning an authenticity score to each image.
This content (images, videos and audio) artificially created by AI is increasingly used for disinformation purposes but also for manipulation and identity fraud.
MEUDON, France, November 22, 2024 -/African Media Agency (AMA)/- On the occasion of the European Cyber Week which is being held in Rennes from November 19 to 21, 2024, the central theme of which is that of artificial intelligence, Thales teams participated in the AID Challenge by distinguishing themselves at second place thanks to the development of a metamodel for detecting images generated by AI. At a time when disinformation is spreading to the media and all sectors of the economy, in light of the generalization of AI techniques, this tool aims to fight against image manipulation for different cases of use such as the fight against identity fraud.
AI-generated images are generated through the use of modern AI platforms (Midjourney, Dall-E, Firefly, etc.). Today, AI technologies have evolved so much that it is almost impossible for the naked eye to distinguish a real image from an AI-generated image. This also applies to video, even in real time. An AI-generated image can therefore constitute an open door for malicious attackers who can use it for identity theft and fraud. Some studies predict that within a few years, deepfakes could cause massive financial losses due to their use for identity theft and fraud. Gartner has estimated that in 2023, around 20% of cyberattacks could include deepfake content as part of disinformation or manipulation campaigns. Their report highlights the rise of deepfakes in financial fraud and advanced phishing attacks.
« The Thales metamodel for detecting deepfakes responds in particular to the problem of identity fraud and the morphing technique. The aggregation of several methods using neural networks, noise detection or even spatial frequencies will make it possible to better secure the growing number of solutions requiring identity verification by biometric recognition. This is a remarkable technological advance, resulting from the expertise of Thales AI researchers. » specifies Christophe Meyer, Senior AI Expert and Technical Director at cortAIx, Thales’ AI accelerator.
The Thales metamodel draws on machine learning techniques, decision trees, and evaluation of the strengths and weaknesses of each model in order to analyze the authenticity of an image. It thus combines different models, including:
- The CLIP (Contrastive Language–Image Pre-training) method which consists of linking images and text by learning to understand how an image and its textual description correspond. In other words, CLIP learns to associate visual elements (like a photo) with words that describe them. To detect deepfakes, CLIP can analyze images and evaluate their compatibility with descriptions in text format, thus identifying inconsistencies or visual anomalies.
- The DNF method which uses current image generation architectures (“diffusion” models) to detect them. Concretely, diffusion models are based on the estimation of noise to add to an image to create a “hallucination” which will create content from nothing. The estimation of this noise can also be used in the detection of images generated by AI.
- The DCT (Discrete Cosine Transform) method is based on the analysis of the spatial frequencies of an image. By transforming the image from spatial space (pixels) to frequency space (like waves), DCT can detect subtle anomalies in the structure of the image, often invisible to the naked eye. They appear during the generation of deepfakes.
The Friendly Hackers team behind this invention is part of cortAIx, Thales’ AI accelerator, with more than 600 AI researchers and engineers, including 150 based on the Saclay plateau and working on critical systems. . The Group’s Friendly Hackers have developed a toolbox, the BattleBox, the objective of which is to facilitate the assessment of the robustness of systems integrating AI against attacks aimed at exploiting the intrinsic vulnerabilities of different data models. AI (including Large Language Models), such as adversary attacks or attacks aimed at extracting sensitive information. To deal with attacks, suitable countermeasures, such as unlearning, federated learning, model watermarking, model robustification are proposed.
The Group was a winner in 2023 as part of the CAID (Conference on Artificial Intelligence for Defense) challenge organized by the DGA, aimed at finding certain data used to train AI, including when it had been deleted from the system for preserve their confidentiality.
Distributed by African Media Agency (AMA) for Thales.
About Thales
Thales (Euronext Paris: HO) is a global leader in high technologies specializing in three business sectors: Defense & Security, Aeronautics & Space, and Cybersecurity & Digital Identity.
It develops products and solutions that contribute to a safer, more environmentally friendly and more inclusive world.
The Group invests nearly 4 billion euros per year in Research & Development, particularly in key areas of innovation such as AI, cybersecurity, quantum, cloud technologies and 6G.
Thales has nearly 81,000 employees in 68 countries. In 2023, the Group achieved a turnover of 18.4 billion euros.
CONTACT
Relations presse
[email protected]
Source : African Media Agency (AMA)
2024-11-22 13:01:00
#Thales #Friendly #Hackers #invent #metamodel #detecting #images #produced #deepfakes #
What challenges does Thales face in detecting increasingly sophisticated deepfakes with their metamodel?
**Interview with Christophe Meyer, Senior AI Expert and Technical Director at cortAIx, Thales’ AI Accelerator**
**Interviewer:** Thank you for joining us, Christophe. Congratulations on Thales’ recent recognition at the European Cyber Week with your innovative metamodel for detecting AI-generated images. Can you tell us a bit about what inspired this technology?
**Christophe Meyer:** Thank you for having me! The inspiration behind the metamodel was the growing threat of disinformation and identity fraud fueled by AI-generated content, particularly deepfakes. As AI technologies have evolved, they have become increasingly capable of creating highly realistic images, videos, and even audio. Our goal was to develop a robust tool that can help identify these manipulated assets and mitigate the risks they pose, especially in critical applications like biometric recognition.
**Interviewer:** That’s intriguing. Can you explain how your metamodel functions in detecting deepfakes?
**Christophe Meyer:** Certainly! Our metamodel aggregates several detection methods. It uses machine learning techniques and evaluates multiple models, each providing an authenticity score for an image. For example, one of the methods we employ is CLIP, which links images to their textual descriptions and can spot inconsistencies. We also utilize diffusion models to analyze noise in images, which is a telltale sign of AI generation. Moreover, we apply Discrete Cosine Transform (DCT) to examine spatial frequencies, detecting subtle anomalies that might escape the naked eye.
**Interviewer:** With deepfakes becoming more sophisticated, how do you foresee the impact of your metamodel in various sectors?
**Christophe Meyer:** Our metamodel has far-reaching implications. In sectors like finance, it can help prevent identity theft and fraud, which are becoming more prevalent due to the rise of deepfakes. Similarly, in media and communications, it can address disinformation issues. As regulations around digital identities and content authenticity become stricter, our tool can serve as a crucial ally in maintaining trust in digital interactions and transactions.
**Interviewer:** That’s a significant contribution indeed! What are the next steps for Thales in this space?
**Christophe Meyer:** We aim to refine our metamodel continually and expand its capabilities. We are also focused on collaborating with industry partners and regulatory bodies to ensure our technology not only meets market needs but also addresses ethical considerations in AI usage. Education and awareness are essential as we navigate these challenges, and we want to lead the charge in promoting responsible AI practices.
**Interviewer:** Thank you, Christophe, for sharing your insights! It’s exciting to see technology being utilized to combat such pressing issues.
**Christophe Meyer:** Thank you! It’s a pleasure to share our work, and we’re eager to make a positive impact through innovation.