Biography

Jonathan is a senior research scientist at Flashbots, where he explores the application of Privacy Enhancing Technologies (PETs) to complex problems such as decentralised collaborative learning and Maximum Extractable Value (MEV) in blockchains. His expertise spans Secure Computing (Trusted Execution Environments, Fully Homomorphic Encryption), Federated Learning, and Verifiable Computing (Zero-Knowledge Proofs, TEEs).

He is also a research fellow at Imperial College London (BioMedIA) and City, University of London (CitAI) where he co-supervises MEng, MSc, and PhD students in Privacy-Preserving Machine Learning and Federated Learning. His work focuses on designing AI systems that ensure data sovereignty and security.

• 2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments

  Details PDF

• A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification

  Details PDF

• A blockchain-orchestrated Federated Learning architecture for healthcare consortia

  Details PDF

• A generic framework for privacy preserving deep learning

  Details PDF Code

• ARIA: On the interaction between Architectures, Aggregation methods and Initializations in federated visual classification

  Details PDF

• Adversarial interference and its mitigations in privacy-preserving collaborative machine learning

  Details PDF

• Contribution Evaluation in Federated Learning: Examining Current Approaches

  Details PDF

• Cooperative AI via Decentralized Commitment Devices

  Details PDF

• End-to-end privacy preserving deep learning on multi-institutional medical imaging

  Details PDF

• Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryption

  Details PDF

• 0xAI: The Odd Couple: How Can Blockchain Help AI

  Wed, Jan 11, 2023, Chailink’s SmartCon 2023

• Joys and Challenges of Adopting PETs

  Wed, Jan 11, 2023, Flashbots Privacy Roast

• Where is Trust in the age of no Trust? - Hardware vs. Software-Based Trusted Compute Approaches

  Tue, Sep 7, 2021, EEA Trusted Compute WG Monthly Webinar

• No Country for Old Data - Data Valuation Considerations for AI/ML

  Wed, Aug 25, 2021, IEEE Healthcare: Blockchain & AI Virtual Series presents Healthcare Data Valuation – Aug 25, 2021

• Overcoming data security and privacy challenges with federated learning

  Wed, Oct 21, 2020, Digital Catapult masterclass

• Secure Computing solutions for Healthcare

  Wed, Oct 14, 2020, City University London, UK - CitAI seminar series

• Privacy-preserving AI in Healthcare

  Wed, Jul 22, 2020, AI for Health News

• Convergence of Blockchain and Secure Computing for Healthcare solutions

  Wed, Sep 4, 2019, EU Blockchain forum

Imperial College London (UK)

PhD student supervion

• Dmitrii Usynin (2020-) - co-supervised with Ben Glocker (ICL) and Georgios Kaissis (TU Munich)
• Vasilis Siomos (2022-) - co-supervised with Giacomo Tarroni (City, University of London)

Labs and tutorials

• ZKML: Introduction to Zero-Knowledge Proofs for Verifiable Machine Learning
• Computer Graphics: OpenGL
• Functional programming in Haskell: Introduction to functional programming
• Java: Introduction to the language

Student projects supervised

• Various undergraduate and MSc projects supervised
• Corporate Partnership Programme Prize in 2023 the Department prize for excellence in project work to Bianca Ganescu (MEng Computing 4), snarkGPT: Zero-Knowledge Proofs for the Inference Phase of Transformers
• Corporate Partnership Programme Prize in 2020 the Department prize for excellence in project work to Dmitrii Usynin (MEng Computing 4 - now PhD student), Privacy-Preserving Machine Learning in a Medical Domain
• Corporate Partnership Programme Awards in 2019 the Department prize for excellence in project work to Cristian Matache (MEng Computing 4), Efficient Design of Machine Learning Hyperparameter Optimizers
• Corporate Partnership Programme Awards in 2019 the Department prize for excellence in project work to Maurizio Zen (MEng JMC 4), Improving Neural Architecture Search with Reinforcement Learning
• New Voice Media Prize in 2018 awarded for an outstanding individual project in the area of data science to Corentin Herbinet (MEng JMC 4), Using Machine Learning techniques to predict the outcome of professional football
• New Voice Media Prize in 2016 awarded for an outstanding individual project in the area of data science to Adrian Draghici (MEng Computing 4), Cloud computing for big data experiments

ISIMA (Engineering School, France)

Courses led

• Software Engineering 101: Git, Debugging with gdb
• C++: Unit Testing (gtest), Template Meta-Programming, Standard Library
• UML: Design Pattern, Class, State, Sequence Diagrams
• Java: Java 7, Swing
• Distributed computing: Cluster (PBS), Grid (EGI)
• GPU Computing: CUDA, SIMD architecture

Student projects supervised

• Various MEng projects supervised covering GPU parallelisation
• Some associated publications (1, 2)

MSc in Computer Science (Blaise Pascal University, France)

Courses led

• Introduction to parallel programming with CUDA

• Academic CV
• Resume

• j.passerat-palmbach@imperial.ac.uk
• https://meet.jit.si
• Huxley Building, 180 Queen's Gate, SW7 2RH