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 about auditing and evaluating black-box algorithms and AIs (or links to papers) in the context of decision-making methods (algorithms, neural-network models, LLMs, etc). In other words, I am interested in auditability, that is: what can or cannot be audited/evaluated, and how.
Recent News
- CACM opinion accepted “Fade to grey: from black-box to AI-antagonistic audits”, to appear Aug. 2026. Draft.
- 2 papers accepted to ICML 2026: Token-Efficient Change Detection in LLM APIs & FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences.
- Applied Network Science 2026 article “LLMs prompted for graphs: hallucinations and generative capabilities”.
- New available postdoc position for the sequoIA chair FANG: bridging audits and AI security, contact me directly.
- ERX project, an AI-driven vending machine that questions the freedom of choice facing AI-based decisions.
- SRDS’25 paper “Robust Fingerprinting of Graphs with FinG”, best paper award.
- ECML’25 paper “P2NIA: Privacy-Preserving Non-Iterative Auditing”.
- 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”, january 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
- ECML/PKDD’26: European Conference on Machine Learning and Data Mining
- AAAI’26: 40th Annual AAAI Conference on Artificial Intelligence
- 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
Awarded publications
- Robust Fingerprinting of Graphs with FinG, with Corentin Hardy and Bruno Sericola. SRDS 2025 best paper award.
- Distributed deep learning on edge-devices: feasibility via adaptive compression, with Corentin Hardy and Bruno Sericola. IEEE NCA 2017 best paper award.
- Archiving Cold Data in Warehouses with Clustered Network Coding, with André, Kermarrec, Le Scouarnec, Straub and van Kempen. Eurosys 2014. Awarded magazine prize “La recherche 2015”, in France.
Audit related projets
- ERX project, an AI-driven vending machine, to question the liberty of choice facing AI-based decisions.
- DigesTube: what have you seen during the JOs depending on your profile? Studying recommendations.
- Co-organized the WAAA workshop on algorithmic audits of algorithms
- Monitoring 2022 elections on YouTube.
- Audited shadow banning practices by Twitter.
- Atelier “Algorithmes en Boite-Noire”, in 2019.