Explainable and Responsible AI


To build more trustworthy AI systems, we investigate how to produce explanations for results returned by AI systems and how to build AI algorithms with guarantees of fairness and privacy, in the setting of varied tasks such as classification, recommendation, resource allocation or matching.


Our activities are structured by several PhD works co-supervised with team members in collaboration with academic or industrial partners : CEA LIST, Nokia Bell Labs, Naver Labs Europe, NUKKAI.
  • Privacy and security vulnerabilities of Semantic Web (PhD funded by the chair)
  • Political ads – audit, detection and impact analysis (PhD funded by the chair)
  • Collaborative Transparency (PhD funded by the chair)
  • Fairness in multi-stakeholder recommendation platforms (Cifre PhD with Naver Labs Europe)
  • Rule learning for formal verification of Deep Neural Networks (PhD funded by CEA LIST)
  • Alarm prediction in communication networks via explainable machine learning (Cifre PhD with Nokia Bell Labs)

We are also developing international collaborations, in particular within the TAILOR european network of excellence on Trustworthy AI in which we have launched coordinating research actions on explainability, privacy and fairness.

For the academic year 2021-2022, we are co-funding with TAILOR the delegation of Radu Ciucanu, who is working on secure protocols for AI algorithms on distributed data e.g., secure federated learning.


  • Round Table “Is Deep Learning explainable” (Organizers: MC Rousset, G. Quénot – Panelists: O. Goga, P.Muhlem). LIG scientific day- October 15th 2020.
  • Round Table “How to buid Trustable AI systems ?” (co-organized with P. Wieczoreck from Minalogic)- Les éclairages de l’IA « Model versus Data Validation ou comment avoir confiance dans l’IA ? »- February 5th 2021.
  • “Contribution of the Chair Explainable and Responsible AI to Trustworthy AI”, MC Rousset, kickoff TAILOR WP3 “Trustworthy AI”. MC Rousset, December 17th 2020.
  • Workshop "Explainable and Responsible AI" organized in hybrid format in Grenoble, with invited researchers from LABRI and IRISA, November 25th 2021


  • R. Ciucanu, P. Lafourcade, G. Marcadet, M. Soare. SAMBA: A Generic Framework for Secure Federated Multi-Armed Bandits. Journal of Artificial Intelligence Research (JAIR) 2022
  • R. Ciucanu, A. Delabrouille, P. Lafourcade, M. Soare. Secure Protocols for Best Arm Identification in Federated Stochastic Multi-Armed Bandits. IEEE Transactions on Dependable and Secure Computing (TDSC) 2022
  • R. Ciucanu, P. Lafourcade, M. Lombard-Platet, M. Soare. Secure Protocols for Cumulative Reward Maximization in Stochastic Multi-Armed Bandits. Journal of Computer Security (JCS) 2022
  • G. Marcadet, R. Ciucanu, P. Lafourcade, M. Soare, S. Amer-Yahia. SAMBA: A System for Secure Federated Multi-Armed Bandits. IEEE International Conference on Data Engineering (ICDE) 2022, Demo
  • R. Ciucanu, M. Soare, S. Amer-Yahia. Implementing Linear Bandits in Off-the-Shelf SQLite. International Conference on Extending Database Technology (EDBT) 2022, Short paper
  • Benjamin Roussillon, Patrick Loiseau. Scalable Optimal Classifiers for Adversarial Settings under Uncertainty. GameSec 2021 - 12th Conference on Decision and Game Theory for Security, Oct 2021, Prague, Czech Republic. pp.1-20.
  • Dong Quan Vu, Patrick Loiseau. Colonel Blotto Games with Favoritism: Competitions with Pre-allocations and Asymmetric Effectiveness. Proceedings of the 22nd ACM Conference on Economics and Computation (ACM EC '21), Jul 2021, Budapest, Hungary. pp.862-863.
  • Johnnatan Messias, Mohamed Alzayat, Balakrishnan Chandrasekaran, Krishna Gummadi, Patrick Loiseau et al. Selfish & Opaque Transaction Ordering in the Bitcoin Blockchain: The Case for Chain Neutrality. IMC 2021 - ACM Internet Measurement Conference, Nov 2021, Virtual Event, France. pp.1-16, ⟨10.1145/3487552.3487823⟩.
  • Vitalii Emelianov, Nicolas Gast, Krishna Gummadi, Patrick Loiseau. On fair selection in the presence of implicit and differential variance. Artificial Intelligence, Elsevier, 2021, 302, pp.1-20.
  • RDF graph anonymization robust to data linkage. Remy Delanaux, Angela Bonifati, Marie-Christine Rousset and Romuald Thion. Proceedings of WISE 2019 (20th International Conference on Web Information Systems Engineering). January 2020, Hong Kong.
  • "Facebook Ads Monitor: An Independent Auditing System for Political Ads on Facebook", Márcio Silva, Lucas Santos de Oliveira, Athanasios Andreou, Pedro Olmo Vaz de Melo, Oana Goga, Fabrício Benevenuto, WWW 2020 (The Web Conference)
  • Path Planning Problems with Side Observations---When Colonels Play Hide-and-Seek. Dong Quan Vu, Patrick Loiseau, Alonso Silva, and Long Tran-Thanh. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI), February 2020.
  • Sihem Amer-Yahia, Shady Elbassuoni, Ahmad Ghizzawi, Ria Mae Borromeo, Emilie Hoareau, Philippe Mulhem: Fairness in Online Jobs: A Case Study on TaskRabbit and Google. EDBT 2020: 510-521
  • Fairness of Scoring in Online Job Marketplaces: Shady Elbassuoni, Sihem Amer-Yahia, Ahmad Ghizzawi. ACM Tansactions in Data Science, 2020
  • Linear Regression from Strategic Data Sources. Nicolas Gast, Stratis Ioannidis, Patrick Loiseau, and Benjamin Roussillon. ACM Transactions on Economics and Computation, 8(2):10:1–10:24, May 2020
  • Towards Designing Cost-Optimal Policies to Utilize IaaS Clouds with Online Learning. Xiaohu Wu, Patrick Loiseau, and Esa Hyytia. IEEE Transactions on Parallel and Distributed Systems, 31(3):501-514, March 2020
  • On Fair Selection in the Presence of Implicit Variance. Vitalii Emelianov, Nicolas Gast, Krishna P. Gummadi, and Patrick Loiseau. In Proceedings of the 21st ACM Conference on Economics and Computation (EC), July 2020.
  • Nonzero-sum Adversarial Hypothesis Testing Games. Sarath Yasodharan, and Patrick Loiseau. In Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS), December 2019.
  • Combinatorial Bandits for Sequential Learning in Colonel Blotto Games. Dong Quan Vu, Patrick Loiseau, and Alonso Silva. In Proceedings of the 58th IEEE Conference on Decision and Control (CDC), December 2019.
  • The Price of Local Fairness in Multistage Selection. Vitalii Emelianov, George Arvanitakis, Nicolas Gast, Krishna Gummadi, and Patrick Loiseau. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), August 2019.
Published on  January 11, 2024
Updated on January 11, 2024