Blaise Delattre

Institute of Science Tokyo

Tokyo, Japan

I am a JSPS Postdoctoral Fellow in Prof. Yang Cao’s group at the Institute of Science Tokyo, Japan. My research focuses on trustworthy AI, with an emphasis on certified robustness, randomized smoothing, Lipschitz-controlled neural networks, and robust foundation-model systems.

I completed my PhD at MILES, LAMSADE, Université Paris-Dauphine PSL, under the supervision of Prof. Alexandre Allauzen and Dr. Quentin Barthélemy. My doctoral work focused on Lipschitz-constrained neural networks and certified robustness.

Research interests: Certified Robustness and Trustworthy AI · Lipschitz Networks and Randomized Smoothing · Robust Foundation Models · Stable and Efficient Deep Learning.

⬇️ Download my CV · 📘 Read my PhD manuscript · 💻 GitHub

news

Oct 21, 2026	ICML 2027 — I will serve as an Area Chair.
Sep 25, 2026	NeurIPS 2026 — Our paper “Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness” has been accepted.
Sep 17, 2026	ICLR 2027 — I will serve as an Area Chair.
Sep 01, 2026	JSPS Postdoctoral Fellowship — I started as a JSPS Postdoctoral Fellow at the Institute of Science Tokyo in September 2026.
Aug 18, 2026	SPReAD grant — I have been awarded a grant under MEXT’s SPReAD (Supporting Pioneering Research through AI for 1,000 Discovery challenges) program for AI for Science.

selected publications

NeurIPS

Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness

Blaise Delattre^*, Hengyu Wu^*, Wei Yang Bryan Lim, and 1 more author

In Advances in Neural Information Processing Systems (NeurIPS). Equal contribution , 2026

Bib HTML

@inproceedings{delattre2026joint,
  title = {Joint Certification for Attributed Graphs: Beyond Topology-Only Robustness},
  author = {Delattre, Blaise and Wu, Hengyu and Lim, Wei Yang Bryan and Cao, Yang},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
}

ICML

Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing

Blaise Delattre, Hengyu Wu, Paul Caillon, and 2 more authors

In International Conference on Machine Learning (ICML), 2026

arXiv Bib HTML

@inproceedings{delattre2026hybrid,
  title = {Certified Robustness under Heterogeneous Perturbations via Hybrid Randomized Smoothing},
  author = {Delattre, Blaise and Wu, Hengyu and Caillon, Paul and Lim, Wei Yang Bryan and Cao, Yang},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
}

AISTATS

Bridging the Theoretical Gap in Randomized Smoothing

Blaise Delattre, Paul Caillon, Erwan Fagnou, and 2 more authors

In The 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025

arXiv Bib HTML

@inproceedings{delattre2025bridging,
  title = {Bridging the Theoretical Gap in Randomized Smoothing},
  author = {Delattre, Blaise and Caillon, Paul and Fagnou, Erwan and Barth{\'e}lemy, Quentin and Allauzen, Alexandre},
  booktitle = {The 28th International Conference on Artificial Intelligence and Statistics (AISTATS)},
  year = {2025},
}

ICLR

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

Blaise Delattre, Alexandre Araujo, Quentin Barthélemy, and 1 more author

In International Conference on Learning Representations (ICLR), 2024

arXiv Bib HTML

@inproceedings{delattre2024lipschitz,
  title = {The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing},
  author = {Delattre, Blaise and Araujo, Alexandre and Barth{\'e}lemy, Quentin and Allauzen, Alexandre},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
}

ICML

Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration

Blaise Delattre, Quentin Barthélemy, Alexandre Araujo, and 1 more author

In International Conference on Machine Learning (ICML), 2023

arXiv Bib HTML

@inproceedings{delattre2023efficient,
  title = {Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration},
  author = {Delattre, Blaise and Barth{\'e}lemy, Quentin and Araujo, Alexandre and Allauzen, Alexandre},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
}

ICLR

A Unified Algebraic Perspective on Lipschitz Neural Networks

Alexandre Araujo, Aaron Havens, Blaise Delattre, and 2 more authors

In International Conference on Learning Representations (ICLR), 2023

arXiv Bib HTML

@inproceedings{araujo2023unified,
  title = {A Unified Algebraic Perspective on Lipschitz Neural Networks},
  author = {Araujo, Alexandre and Havens, Aaron and Delattre, Blaise and Allauzen, Alexandre and Hu, Bin},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
}

ICML

A Dynamical System Perspective for Lipschitz Neural Networks

Laurent Meunier^*, Blaise Delattre^*, Alexandre Araujo^*, and 1 more author

In International Conference on Machine Learning (ICML). Equal contribution , 2022

arXiv Bib HTML

@inproceedings{meunier2022dynamical,
  title = {A Dynamical System Perspective for Lipschitz Neural Networks},
  author = {Meunier, Laurent and Delattre, Blaise and Araujo, Alexandre and Allauzen, Alexandre},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
}