Publications related to Privacy and Confidentiality in Machine Learning and Data Analysis: Understanding Risks and Developing Protections

Related publications (11)

Robust and Personalized Federated Learning: Handling Data Corruption and Heterogeneity

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling collaborative model training across decentralized devices while preserving data privacy. However, FL's success is highly contingent on the quality and integrity ...

EPFL2025

Learning transferable land cover semantics for open vocabulary interactions with remote sensing images

Devis Tuia, Javiera Francisca Castillo Navarro, Valérie Zermatten

Why should we confine land cover classes to rigid and arbitrary definitions? Land cover mapping is a central task in remote sensing image processing, but the rigorous class definitions can sometimes restrict the transferability of annotations between datas ...

2025

Noiseless Privacy-Preserving Decentralized Learning

Anne-Marie Kermarrec, Rafael Pereira Pires, Rishi Sharma, Marinus Abraham de Vos, Sayan Biswas

Decentralized learning (DL) enables collaborative learning without a server and without training data leaving the users' devices. However, the models shared in DL can still be used to infer training data. Conventional defenses such as differential privacy ...

Privacy Enhancing Technologies Symposium Advisory Board2024

WildCLIP: Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models

Devis Tuia, Alexander Mathis, Marc Conrad Russwurm, Valentin Alexandre Guy Gabeff

WildCLIP: Scene and animal attribute retrieval from camera trap data with domain-adapted vision-language models ############# Authors: Valentin Gabeff, Marc Russwurm, Devis Tuia & Alexander Mathis Affiliation: EPFL Date: January, 2024 Link to the article: ...

Zenodo2024

Fast Streaming Transducer ASR Prototyping via Knowledge Distillation with Whisper

Juan Pablo Zuluaga Gomez

The training of automatic speech recognition (ASR) with little to no supervised data remains an open question. In this work, we demonstrate that streaming Transformer-Transducer (TT) models can be trained from scratch in consumer and accessible GPUs in the ...

Association for Computational Linguistics (ACL)2024

Nuance Matters: Probing Epistemic Consistency in Causal Reasoning

Boi Faltings, Shaobo Cui, Luca Mouchel, Yiyang Feng

Previous research on causal reasoning often overlooks the subtleties crucial to understanding causal reasoning. To address this gap, our study introduces the concept of causal epistemic consistency, which focuses on the self-consistency of Large Language M ...

2024

Constrained Zero-Shot Neural Architecture Search on Small Classification Dataset

Liza Carol Andrea Dunbar

The rapid evolution of Deep Learning (DL) has brought about significant transformations across scientific domains, marked by the development of increasingly intricate models demanding powerful GPU platforms. However, edge applications like wearables and mo ...

IEEE2024

A Blockchain-Based Interoperable Architecture for IoT with Selective Disclosure of Information

Shailesh Mishra

With the improvement of Internet of Things (IoT) technologies, services, and applications, there is a proliferation of access to smart devices in everyday life. However, granting access and controlling access rights for each resource is challenging in high ...

IEEE Computer Society2023

Harnessing data science to improve molecular structure elucidation from tandem mass spectrometry

Fernando Perez Cruz, Guillaume Romain Obozinski, Marco Volpi

Compound structural identification for non-targeted screening of organic molecules in complex mixtures is commonly carried out using liquid chromatography coupled to tandem mass spectrometry (UHPLC-HRMS/MS and related techniques). Instrumental developments ...

2023

giotto-tda: A Topological Data Analysis Toolkit for Machine Learning and Data Exploration

Guillaume Andréa Jérémie Tauzin, Kathryn Hess Bellwald, Anibal Maximiliano Medina Mardones

We introduce giotto-tda, a Python library that integrates high-performance topological data analysis with machine learning via a scikit-learn {compatible API and state-of-the-art C++ implementations. The library's ability to handle various types of data is ...

2021

SPHN/PHRT - MedCo in Action: Empowering the Swiss Molecular Tumor Board with Privacy-Preserving and Real-Time Patient Discovery

Jean-Pierre Hubaux, Jacques Fellay, Juan Ramón Troncoso-Pastoriza, Joao André Gomes de Sá e Sousa, Mickaël Misbach, Francesco Marino

MedCo is the first operational system that makes sensitive medical-data available for research in a simple, privacy-conscious and secure way. It enables a consortium of clinical sites to collectively protect their data and to securely share them with inves ...

IOS PRESS2020