LLMs hallucinate graphs too! (here prompted for the Karate Club Graph). Extended V2 here.

I am a researcher at Inria, Brittany, France (ARTISHAU team). I am leading the scientific council of the Société Informatique de France, and I am the president of an association promoting free software for mail/hosting in Brittany.

My current research is auditing and evaluating black-box algorithms and AIs (or links to papers) in the context of of decision-making methods (neural-network models, LLMs, etc). In other words, I am interested in auditability, that is: what can or cannot be audited/evaluated, and how. I co-organized the WAAA workshop on algorithmic audits of algorithms, in an attempt to link several research domains on this societal question.

• Monitoring 2022 elections on YouTube.
• Audited shadow banning pratices by Twitter.
• Atelier “Algorithmes en Boite-Noire”, in 2019.

Recent News

• ICML’25 paper “Robust ML Auditing using Prior Knowledge”; spotlight top 2,6% papers!
• AAAI’25 paper “Queries, Representation & Detection: The Next 100 Model Fingerprinting Schemes”.
• Interview for the Data Skeptic podcast on “LLMs hallucinte graphs too”, jannuary 2025.
• Interview dans Les Echos “Face à des IA trop humaines, le défi de l’identification” ou en PDF, 12 nov 2024.
• French ANR project starting, on “passive or active monitoring and auditing of models” (4 years duration). Recruiting a PhD candidate and an engineer. More info: bit.ly/PACMAM

Last PCs

• ECAI’25: 28TH European conference on artificial intelligence
• ECML/PKDD’25: European Conference on Machine Learning and Data Mining
• KDD’24: 30TH ACM SIGKDD conference on knowledge discovery and data mining
• ECAI’24: 27TH European conference on artificial intelligence
• AIsec’24: 17TH ACM Workshop on Artificial Intelligence and Security
• ECML/PKDD’24: European Conference on Machine Learning and Data Mining
• SDM’24: SIAM International Conference on Data Mining

Selected publications

• Setting the Record Straighter on Shadow Banning, Erwan Le Merrer, Benoît Morgan, Gilles Trédan. In INFOCOM, 2021. PDF
• Remote Explainability faces the bouncer problem, Erwan Le Merrer, Gilles Trédan. In Nature Machine Intelligence, 2020. PDF
• Adversarial Frontier Stitching for Remote Neural Network Watermarking, Erwan Le Merrer, Patrick Perez, Gilles Trédan. In Neural Comput & Applic 32, 9233–9244, 2020. PDF
• Second order centrality: Distributed assessment of nodes criticity in complex networks, AM Kermarrec, E Le Merrer, B Sericola, G Trédan. Computer Communications 34 (5), 619-628, 2011. PDF & code in NetworkX