no code implementations • 24 Nov 2024 • Olivia Ma, Jonathan Passerat-Palmbach, Dmitrii Usynin
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data.
no code implementations • 2 Oct 2024 • Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni
By integrating weight standardization and channel attention in the backbone model, ANFR offers a novel and versatile approach to the challenge of statistical heterogeneity.
no code implementations • 9 Feb 2024 • Bianca-Mihaela Ganescu, Jonathan Passerat-Palmbach
We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy.
1 code implementation • 24 Nov 2023 • Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni
Federated Learning (FL) is a collaborative training paradigm that allows for privacy-preserving learning of cross-institutional models by eliminating the exchange of sensitive data and instead relying on the exchange of model parameters between the clients and a server.
no code implementations • 16 Nov 2023 • Vasilis Siomos, Jonathan Passerat-Palmbach
Federated Learning (FL) has seen increasing interest in cases where entities want to collaboratively train models while maintaining privacy and governance over their data.
no code implementations • 14 Nov 2023 • Xinyuan Sun, Davide Crapis, Matt Stephenson, Barnabé Monnot, Thomas Thiery, Jonathan Passerat-Palmbach
Credible commitment devices have been a popular approach for robust multi-agent coordination.
no code implementations • 27 Feb 2022 • George-Liviu Pereteanu, Amir Alansary, Jonathan Passerat-Palmbach
This work presents a novel protocol for fast secure inference of neural networks applied to computer vision applications.
no code implementations • 21 Dec 2021 • Dmitrii Usynin, Alexander Ziller, Daniel Rueckert, Jonathan Passerat-Palmbach, Georgios Kaissis
The utilisation of large and diverse datasets for machine learning (ML) at scale is required to promote scientific insight into many meaningful problems.
no code implementations • 2 Dec 2021 • Stefán Páll Sturluson, Samuel Trew, Luis Muñoz-González, Matei Grama, Jonathan Passerat-Palmbach, Daniel Rueckert, Amir Alansary
The robustness of federated learning (FL) is vital for the distributed training of an accurate global model that is shared among large number of clients.
no code implementations • 6 Sep 2021 • Ashly Lau, Jonathan Passerat-Palmbach
Differential privacy provides strong privacy guarantees for machine learning applications.
no code implementations • 10 Dec 2020 • Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel, Dmitrii Usynin, Andrew Trask, Ionésio Da Lima Costa Junior, Jason Mancuso, Marcus Makowski, Daniel Rueckert, Rickmer Braren, Georgios Kaissis
The utilisation of artificial intelligence in medicine and healthcare has led to successful clinical applications in several domains.
no code implementations • 15 Nov 2020 • Harry Cai, Daniel Rueckert, Jonathan Passerat-Palmbach
While the initial model might belong solely to the actor bringing it to the network for training, determining the ownership of the trained model resulting from Federated Learning remains an open question.
no code implementations • 10 Nov 2020 • Veneta Haralampieva, Daniel Rueckert, Jonathan Passerat-Palmbach
This work provides a comprehensive review of existing frameworks based on secure computing techniques in the context of private image classification.
no code implementations • 17 Sep 2020 • Matei Grama, Maria Musat, Luis Muñoz-González, Jonathan Passerat-Palmbach, Daniel Rueckert, Amir Alansary
In this work, we implement and evaluate different robust aggregation methods in FL applied to healthcare data.
Cryptography and Security
no code implementations • 12 Oct 2019 • Jonathan Passerat-Palmbach, Tyler Farnan, Robert Miller, Marielle S. Gross, Heather Leigh Flannery, Bill Gleim
We propose a novel architecture for federated learning within healthcare consortia.
3 code implementations • 9 Nov 2018 • Theo Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason Mancuso, Daniel Rueckert, Jonathan Passerat-Palmbach
We detail a new framework for privacy preserving deep learning and discuss its assets.
no code implementations • 8 Jun 2018 • Amir Alansary, Loic Le Folgoc, Ghislain Vaillant, Ozan Oktay, Yuanwei Li, Wenjia Bai, Jonathan Passerat-Palmbach, Ricardo Guerrero, Konstantinos Kamnitsas, Benjamin Hou, Steven McDonagh, Ben Glocker, Bernhard Kainz, Daniel Rueckert
Navigating through target anatomy to find the required view plane is tedious and operator-dependent.
no code implementations • 25 Mar 2018 • Giacomo Tarroni, Ozan Oktay, Wenjia Bai, Andreas Schuh, Hideaki Suzuki, Jonathan Passerat-Palmbach, Antonio de Marvao, Declan P. O'Regan, Stuart Cook, Ben Glocker, Paul M. Matthews, Daniel Rueckert
The results show the capability of the proposed pipeline to correctly detect incomplete or corrupted scans (e. g. on UK Biobank, sensitivity and specificity respectively 88% and 99% for heart coverage estimation, 85% and 95% for motion detection), allowing their exclusion from the analysed dataset or the triggering of a new acquisition.
no code implementations • 21 Aug 2017 • Martin Rajchl, Lisa M. Koch, Christian Ledig, Jonathan Passerat-Palmbach, Kazunari Misawa, Kensaku MORI, Daniel Rueckert
To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort.
no code implementations • 15 Nov 2016 • Sofia Ira Ktena, Sarah Parisot, Jonathan Passerat-Palmbach, Daniel Rueckert
In this work we explore a method based on graph edit distance for evaluating graph similarity, when correspondences between network elements are unknown due to different underlying subdivisions of the brain.
no code implementations • 10 Nov 2016 • Sarah Parisot, Jonathan Passerat-Palmbach, Markus D. Schirmer, Boris Gutman
Understanding brain connectivity in a network-theoretic context has shown much promise in recent years.
no code implementations • 3 Jun 2016 • Martin Rajchl, Matthew C. H. Lee, Franklin Schrans, Alice Davidson, Jonathan Passerat-Palmbach, Giacomo Tarroni, Amir Alansary, Ozan Oktay, Bernhard Kainz, Daniel Rueckert
The availability of training data for supervision is a frequently encountered bottleneck of medical image analysis methods.
no code implementations • 25 May 2016 • Martin Rajchl, Matthew C. H. Lee, Ozan Oktay, Konstantinos Kamnitsas, Jonathan Passerat-Palmbach, Wenjia Bai, Mellisa Damodaram, Mary A. Rutherford, Joseph V. Hajnal, Bernhard Kainz, Daniel Rueckert
In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations.
no code implementations • 29 Apr 2016 • Lisa M. Koch, Martin Rajchl, Wenjia Bai, Christian F. Baumgartner, Tong Tong, Jonathan Passerat-Palmbach, Paul Aljabar, Daniel Rueckert
Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets.