Sayan Biswas Sayan Biswas
About Me Publications News & Updates CV

About Me

I am a Postdoctoral Researcher in the Scalable Computing Systems (SaCS) lab at EPFL, Switzerland, led by Prof. Anne-Marie Kermarrec. I completed my PhD in Computer Science at INRIA and École Polytechnique in France under the supervision of Prof. Catuscia Palamidessi. Prior to that, I studied mathematics at the University of Bath in the UK, where I obtained my M.Math with a First-Class Honours. During my PhD, I have been a Visiting Scholar at the School of Computing at Macquarie University in Sydney, Australia (hosted by Prof. Annabelle McIver and Dr. Natasha Fernandes) and at WMG at The University of Warwick in Coventry, England (hosted by Prof. Carsten Maple and Prof. Graham Cormode).

My research primarily centres on designing secure and trustworthy distributed systems for analysing data and training ML models in decentralized frameworks. My current research interests revolve around decentralized learning, federated learning, and trustworthy distributed systems, with a particular emphasis on aspects of privacy, fairness, and personalization.

I study, talk, and do mathematics most of the time; when not, I am typically immersed in techno music, chess, cricket, philosophy, puzzles, or stand-up comedy. Lately, I’ve rekindled my love for (non-academic) reading and have become a collector of seemingly useless facts from all corners of life — because who doesn’t need to know how often penguins defecate? I am also trying to learn French with limited success so far. The list of some of my current favourite results and theorems in mathematics (a list that, obviously, everyone should maintain) includes:

Publications

Peer-reviewed Conferences
2025
“Mitigating Membership Inference Vulnerability in Iterative Federated Clustering Algorithm”
Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi
Workshop on Recent Advances in Resilient and Trustworthy ML-Driven Systems (ARTMAN) @ CCS 2025
2025
“Robust ML Auditing using Prior Knowledge”
Jade Garcia Bourrée, Augustin Godinot, Sayan Biswas, Anne-Marie Kermarrec, Erwan Le Merrer, Gilles Tredan, Martijn de Vos, Milos Vujasinovic
International Conference on Machine Learning (ICML) 2025
2025
“Low-Cost Privacy-Aware Decentralized Learning”
Sayan Biswas, Davide Frey, Romaric Gaudel, Anne-Marie Kermarrec, Dimitri Lerévérend, Rafael Pires, Rishi Sharma, François Taïani
Privacy Enhancing Technologies Symposium (PoPETs) 2025, Issue 3
2025
“Boosting Asynchronous Decentralized Learning with Model Fragmentation”
Sayan Biswas, Anne-Marie Kermarrec, Alexis Marouani, Rafael Pires, Rishi Sharma, Martijn de Vos
ACM Web Conference (WWW) 2025
2025
“Fair Decentralized Learning”
Sayan Biswas, Anne-Marie Kermarrec, Rishi Sharma, Thibaud Trinca, Martijn de Vos
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2025
2025
“Noiseless Privacy-Preserving Decentralized Learning”
Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec, Laurent Massoulie, Rafael Pires, Rishi Sharma, Martijn de Vos
Privacy Enhancing Technologies Symposium (PoPETs) 2025, Issue 1
2023
“Tight Differential Privacy Guarantees for the Shuffle Model with k-Randomized Response”
Sayan Biswas, Kangsoo Jung, Catuscia Palamidessi
International Symposium on Foundations and Practice of Security (FPS) 2023
2023
“PRIVIC: A privacy-preserving method for incremental collection of location data”
Sayan Biswas, Catuscia Palamidessi
Privacy Enhancing Technologies Symposium (PoPETs) 2024
2023
“Group privacy for Personalized Federated Learning”
Filippo Galli, Sayan Biswas, Kangsoo Jung, Tommaso Cucinotta, Catuscia Palamidessi
International Conference on Information Systems Security and Privacy (ICISSP) 2023
2022
“Impact of Sampling on Locally Differentially Private Data Collection”
Sayan Biswas, Graham Cormode, Carsten Maple
Competitive Advantage in the Digital Economy (CADE) 2022
2022
“Tight Differential Privacy Blanket for Shuffle Model”
Sayan Biswas, Kangsoo Jung, Catuscia Palamidessi
Competitive Advantage in the Digital Economy (CADE) 2022
2021
“An Incentive Mechanism for Trading Personal Data in Data Markets”
Sayan Biswas, Kangsoo Jung, Catuscia Palamidessi
International Colloquium on Theoretical Aspects of Computing (ICTAC) 2021
Journals
2024
“A Privacy-Preserving Querying Mechanism with High Utility for Electric Vehicles”
Ugur Ilker Atmaca, Sayan Biswas, Carsten Maple, Catuscia Palamidessi
IEEE Open Journal of Vehicular Technology, Volume 5, pp 262–277
2023
“Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond”
Filippo Galli, Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi, Tommaso Cucinotta
Springer Nature Computer Science, Volume 4, Issue 6, Article 831 (2023)
Book Sections
2021
“Establishing the Price of Privacy in Federated Data Trading”
Kangsoo Jung, Sayan Biswas, Catuscia Palamidessi
Protocols, Strands, and Logic, pp 232–250, LNCS 13066, Springer
Non-archival Workshops
2024
“Bayes’ capacity as a measure for reconstruction attacks in federated learning”
Sayan Biswas, Mark Dras, Pedro Faustini, Natasha Fernandes, Annabelle McIver, Catuscia Palamidessi, Parastoo Sadeghi
2023
“PRIVIC: A privacy-preserving method for incremental collection of location data”
Sayan Biswas, Catuscia Palamidessi
Theory and Practice of Differential Privacy (TPDP) 2023 — September 27–28, 2023; Boston, USA
2023
“On the adaptive sensitivity of differentially private machine learning”
Filippo Galli, Sayan Biswas, Kangsoo Jung, Tommaso Cucinotta, Catuscia Palamidessi
4th Workshop on Privacy-Preserving AI (PPAI) @ AAAI 2023 — February 13, 2023; Washington DC, USA
2022
“Group privacy for Personalized Federated Learning”
Filippo Galli, Sayan Biswas, Kangsoo Jung, Tommaso Cucinotta, Catuscia Palamidessi

News & Updates

Oct ’23
Moving to Lausanne, Switzerland to start as a Postdoctoral Researcher at the SaCS lab at EPFL, supervised by Anne-Marie Kermarrec, working on privacy-preserving decentralised models.
Oct ’23
Successfully defended my PhD thesis “Understanding and optimizing the trade-off between privacy and utility from a foundational perspective” — awarded the title of Doctor of Computer Science from École Polytechnique and Institut Polytechnique de Paris!
Photo ft. the official moment of change from “Mr.” to “Dr.”
Sep ’23
Visiting Annabelle McIver and Natasha Fernandes at Macquarie University, Sydney, studying information leakage from differentially private mechanisms and doing lots of fun maths!
Aug ’23
Paper “PRIVIC: A privacy-preserving method for incremental collection of location data” selected for presentation at TPDP 2023 in Boston, USA (September 27–28, 2023).
Aug ’23
Paper “PRIVIC” accepted for publication at the 24th Privacy Enhancing Technologies Symposium (PETS 2024), Bristol, UK, July 2024.
Jul ’23
Presented ongoing work “Characterizing the information leakage from gradient updates in federated learning” at the FedMalin seminar (online, July 10, 2023).
Photo illustrating: “When someone asks a question during your talk, first have some tea.”
Feb ’23
Presented position paper “On the adaptive sensitivity of differentially private machine learning” at the 4th AAAI Workshop on Privacy-Preserving AI (PPAI-23), Washington DC, USA.
Dec ’22
Presented “Group privacy for personalized federated learning” at FL-NeurIPS 2022, New Orleans, USA.
Nov ’22
Presented “Group privacy for personalized federated learning” at the Privacy Preserving Machine Learning (PPML) Workshop at Meta, Paris (November 9, 2022).
Photo ft. three of the five co-authors who struggle to pose elegantly.
Oct ’22
Talk on “A privacy-preserving method for incremental collection of location data: Differential Privacy and beyond” at the 7th Franco-Japanese Cybersecurity Workshop, Tokyo, Japan (October 24, 2022).
Photo ft. an underslept, overtravelled, and perpetually excited Sayan.
Aug ’22
Designed and delivered a hands-on session on differential privacy with federated learning at IDESSAI 2022, Saarbrücken, Germany (August 29 – September 2, 2022).
The course received a special mention as the most liked course in the summer school. :)
Aug ’22
Won the Best Paper Award for “Impact of Sampling on Locally Differentially Private Data Collection” at CADE 2022, Venice, Italy (June 13–15, 2022).
Award certificate.
Jun ’22
Presented ongoing work on “Three-way optimization of privacy and utility of location data” at APVP 2022, Chatenay sur Seine, France (June 15, 2022).
Photo ft. the most Baroque setting and the most non-Baroque outfit.
Jun ’22
Presented “Impact of Sampling on Locally Differentially Private Data Collection” at CADE 2022, Venice, Italy (June 13–15, 2022).
Photo ft. an elated Sayan explaining differential privacy to the crowd.