{"id":13615,"date":"2024-11-20T09:17:43","date_gmt":"2024-11-20T08:17:43","guid":{"rendered":"https:\/\/www.uni.lu\/snt-en\/?post_type=news&p=13615"},"modified":"2024-11-20T09:17:45","modified_gmt":"2024-11-20T08:17:45","slug":"leading-the-way-in-making-ai-trustworthy","status":"publish","type":"news","link":"https:\/\/www.uni.lu\/snt-en\/news\/leading-the-way-in-making-ai-trustworthy\/","title":{"rendered":"Leading the way in making AI trustworthy"},"content":{"rendered":"\n
\n

<\/p>\n\n\n\n

How do you evaluate the robustness of an Artificial Intelligence system against security attacks? This question is at the heart of an SnT paper that was recently awarded as spotlight paper at the prestigious NeurIPS conference.<\/p>\n\n\n\n

More than 15,000 papers were submitted for this event, and 25% have been accepted for publications. Only 3% have been selected as a spotlight.<\/p>\n\n\n\n

\u201cThis is the most prestigious publication we are rewarded, after more than five years of research investment in the field of AI trustworthiness\u201d, says a delighted Maxime Cordy<\/a>, Research Scientist and co-author of the article with Thibault Simonetto<\/a> and Salah Ghamizi.<\/p>\n\n\n\n

Keeping up with AI technology<\/strong><\/p>\n\n\n\n

For years, SnT has been working on developing various aspects of AI technology and its application to areas of economic importance such as Fintech, Cybersecurity, Space Systems and Autonomous Systems.<\/p>\n\n\n\n

An important element of this work is to make AI technology more trustworthy. From ensuring that Ai tools are unbiased, robust and explainable, to creating solutions that protect AI systems from security attacks.<\/p>\n\n\n\n

As an increasing number of sectors use AI systems in their processes, it’s important these are secure. Take an AI system that has the objective of monitoring transactions to detect money laundering, for example. A security attack could mean that this fraudulent transaction would go unnoticed. This is called an evasion attack, where “noise” is created in the data so that AI can’t do its job properly.<\/p>\n\n\n\n

\n
\n
\n
\n \u201f<\/span>\n Our research proposes a new approach which sets new standards for assessing the robustness of tabular AI.\u201d\n<\/blockquote>\n
\n \n\"Maxime <\/figure><\/div>\n\n
\n

Maxime Cordy<\/p>\n\n\n

Research Scientist<\/p>\n\n

\n \n \n View profile<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n<\/div>\n <\/figure>\n <\/div>\n<\/section>\n\n\n

\u201cThe difficulty is to make these simulated attacks effective and realistic. Our research takes an important step in this direction and proposes a new approach \u2013 Constrained Adaptive Attack – which sets new standards for assessing the robustness of tabular AI\u201d, explains Maxime Cordy. Tabular AI systems deal with data presented in tables (like in database and excel sheets) and are therefore omnipresent in the industry.<\/p>\n\n\n\n

From a project with BGL BNP Paribas to scientific recognition<\/strong><\/p>\n\n\n\n

The paper represents the pinnacle of Thibault Simonetto’s PhD journey at SnT, and also follows the partnership<\/a> announced in January 2024 with BGL BNP Paribas. The interdisciplinary research centre supports the bank in developing an intelligent monitoring system for the AI solutions implemented in its services.<\/p>\n\n\n\n

\u201cThis paper is an important contribution to the realization of our research program and the proposed approach is applicable to the banking AI systems that operate on industrial scale data. This success emphasizes the benefit of a partnership between Industry and academia\u201d comments Anne Goujon, Head of Data Science Laboratory at BGL BNP Paribas.<\/p>\n\n\n\n

The Serval research group, in which Maxime Cordy works, is experiencing a particularly dynamic period. Another of his papers has been accepted as a \u201cbenchmark and dataset\u201d by NeurIPS. This contribution develops a suite of benchmarks for evaluating the ability of defense algorithms to protect tabular AI systems against attacks.<\/p>\n\n\n\n

Thanks to these two distinctions at the NeurIPS conference, SnT receives a publication at one of the leading AI conferences where it had not previously been published. \u201cIn general, AI trustworthiness is a huge topic in Europe right now. This spotlight, together with our publications, demonstrates our legitimacy, as experts, to work on this topic and support society in the AI transition\u201d, adds Maxime Cordy.<\/p>\n\n\n\n

Two other SnT papers have been selected for the NeurIPS conference. These are publications by the CVI2 research group, produced in partnership with Artec3D and POST respectively.<\/p>\n\n\n\n

\n
\n
\n
\n \u201f<\/span>\n Four papers have been accepted this year, which is exceptional and positions SnT at contributor to the AI field at top-level.\u201d\n<\/blockquote>\n
\n \n\"Yves <\/figure><\/div>\n\n
\n

Yves Le Traon<\/p>\n\n\n

Director of the SnT<\/p>\n\n

\n \n \n View profile<\/span>\n <\/span>\n <\/use><\/svg> <\/a>\n<\/div>\n<\/div>\n <\/figure>\n <\/div>\n<\/section>\n\n\n

\u201cIn total, four papers have been accepted this year, which is exceptional and positions SnT as contributor to the AI field at a top-level\u201d, stresses Yves Le Traon<\/a>, Director of the SnT.<\/p>\n\n\n\n

\u201cThese achievements show that getting research and industry working together can lead to high-quality scientific results, contrary to an old prejudice. This requires trust, mutual understanding and a willingness to cooperate in the long term between research and industry”, adds Carlo Duprel<\/a>, Head of SnT Technology Transfer Office.<\/p>\n\n\n\n