After winning the 2023 edition of the Challenge organized by the AID (Defense 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 increasing 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 #
How does Thales plan to address the growing challenges of malicious AI-generated content in cybersecurity?
**Interview with Christophe Meyer, Senior AI Expert and Technical Director at cortAIx, Thales**
**Interviewer:** Thank you for joining us today, Christophe. Thales has made headlines recently with the development of a metamodel for detecting AI-generated images, particularly deepfakes. Could you explain to us what motivated your team to focus on this technology?
**Christophe Meyer:** Thank you for having me. The rise of AI-generated images and videos poses significant risks, particularly in terms of identity fraud and disinformation. As technology evolves, deepfakes become increasingly sophisticated, making it nearly impossible for the average person to differentiate between real and manipulated content. Our motivation stemmed from a need to combat these threats and enhance security measures across various applications, especially those involving biometric recognition.
**Interviewer:** That makes sense. Could you elaborate on how your metamodel works in detecting these deepfakes?
**Christophe Meyer:** Absolutely. Our metamodel utilizes an aggregation of various detection techniques, each contributing to the overall authenticity score of an image. We employ methods such as CLIP, which connects images to text descriptions, and DNF, which uses noise estimation from current image generation architectures. Additionally, we implement Discrete Cosine Transform (DCT) to analyze the spatial frequencies of images. By combining these approaches, we can identify inconsistencies and anomalies indicative of deepfakes more effectively.
**Interviewer:** It sounds like a sophisticated approach. What are the potential real-world applications for this technology?
**Christophe Meyer:** There are numerous applications. Our metamodel can be pivotal in sectors such as finance, where identity verification is crucial. It can also play a significant role in media organizations, helping them ensure the integrity of the information and images they publish. Furthermore, any field that relies on visual content and requires authenticity assurance can benefit from our technology.
**Interviewer:** Given the increasing prevalence of deepfakes, how do you view the future of cybersecurity in relation to AI-generated content?
**Christophe Meyer:** The future is certainly challenging. As AI tools become more accessible, malicious use will inevitably rise. Organizations must be proactive in investing in advanced detection technologies like ours. It’s not just about combatting threats today; it’s about building a robust framework for the future to ensure the integrity of our digital interactions. Continuous R&D will be critical in staying ahead of these evolving threats.
**Interviewer:** Thank you, Christophe. It’s clear that Thales is at the forefront of addressing these challenges. We look forward to seeing how your technology develops further in the fight against disinformation.
**Christophe Meyer:** Thank you for your interest. We are committed to creating a safer, more trustworthy digital environment and appreciate the opportunity to share our work.
