OLFEO ANNOUNCES THE START OF PRODUCTION OF THE RAPID METIS PROJECT

A project that allows it to incorporate AI and machine learning into the creation of its database of domains and URLs and optimize internal classificationperformance .

Olfeo offers a web security gateway to secure and optimize corporate internet traffic. It determines the risk posed by a website accessed by a user in order to apply a corresponding action: information about the risk involved, blocking, etc.

With a database of over 20 million domains, corresponding to hundreds of millions of URLs, Olfeo is the only French company to offer a database of websites that is finely categorized according to usage and the French legal framework. Used by over 1,000 medium-sized businesses and government agencies, Olfeo is the leading web proxy in France.

The domain database is the nerve center of Olfeo's solution. Its accuracy and relevance are among Olfeo's key differentiators. It is therefore essential to ensure its quality and completeness over time. The current approach is based on pre-classification by keywords where possible, but always verified by manual classification. This allows us to achieve unparalleled classification quality, but with the exponential growth of new domains being created, this solution needs to be reinforced.

With 70 million new domains created worldwide every month—including 13 million malicious domains—and dynamic content evolution over time, Olfeo has decided to implement additional techniques to continue ensuring impeccable database quality despite the large volume of new content generated, while preparing for a European expansion of the solution.

The METIS project, with a budget of €1 million, co-financed by the RAPID (Dual Innovation Support Scheme) program and supported by the Defense Innovation Agency of the French Ministry of Armed Forces and the Directorate General of Armament, was launched in 2020. It aims to implement AI and machine learning algorithms to improve the performance of Olfeo's internal classification tools. The project includes a major innovation dimension around data classification and machine learning methods to identify the category to be associated with a URL based on analysis of the web page content.

Carried out in collaboration with the University of Reims Champagne-Ardenne and the computer science laboratory at the University of Grenoble Alpes over a period of three years, the project combined exploration of the state of the art in semantic analysis and classification, the implementation of automated processing procedures, training of various machine learning models using existing Olfeo data, and finally the deployment of a deep learning model that optimized content recognition rates.

The project fully met its objectives. The relevance of the classification was improved by up to 30% for certain types of content, while maintaining the quality of the existing database with a URL recognition rate of nearly 100%. These results enabled the classification algorithm to be integrated into the Olfeo pre-qualification tool.

Olfeo continues to pursue a dual approach, combining classification using machine learning techniques while allowing humans to retain control over the final classification. With the increasing accuracy of automatic classification, Olfeo is paving the way for automatic validation of certain types of content in the near future.

"The experience gained by Olfeo on issues as important as AI is excellent and bodes well for great opportunities in the future, given the promising context. At a time when the AI bubble is bursting, with ChatGPT and the like, it is crucial for a company that aims to become aFrench and European leader in cybersecurity to master these issues and leverage their strength," says Alexandre Souillé, CEO and founder of Olfeo.