Publications (20)
IBM Federated Learning: an Enterprise Framework White Paper V0.1
Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas +21
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume. How…
Adversarial Robustness Toolbox v1.0.0
Maria-Irina Nicolae, Mathieu Sinn, Minh Ngoc Tran +9
Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision…
Certified Federated Adversarial Training
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn +2
In federated learning (FL), robust aggregation schemes have been developed to protect against malicious clients. Many robust aggregation schemes rely on certain numbers of benign c…
Multi-task additive models with shared transfer functions based on dictionary learning
Alhussein Fawzi, Mathieu Sinn, Pascal Frossard
Additive models form a widely popular class of regression models which represent the relation between covariates and response variables as the sum of low-dimensional transfer funct…
FAT: Federated Adversarial Training
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn +1
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML). Adversarial training has emerged, so far, as…
Exploring the Hyperparameter Landscape of Adversarial Robustness
Evelyn Duesterwald, Anupama Murthi, Ganesh Venkataraman +2
Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges o…
One button machine for automating feature engineering in relational databases
Hoang Thanh Lam, Johann-Michael Thiebaut, Mathieu Sinn +3
Feature engineering is one of the most important and time consuming tasks in predictive analytics projects. It involves understanding domain knowledge and data exploration to disco…
Detecting Change-Points in Time Series by Maximum Mean Discrepancy of Ordinal Pattern Distributions
Mathieu Sinn, Ali Ghodsi, Karsten Keller
As a new method for detecting change-points in high-resolution time series, we apply Maximum Mean Discrepancy to the distributions of ordinal patterns in different parts of a time…
Automated Robustness with Adversarial Training as a Post-Processing Step
Ambrish Rawat, Mathieu Sinn, Beat Buesser
Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging. As a step towards…
Kolmogorov-Sinai entropy from the ordinal viewpoint
Karsten Keller, Mathieu Sinn
In the case of ergodicity much of the structure of a one-dimensional time-discrete dynamical system is already determined by its ordinal structure. We generally discuss this phenom…
Learning Correlation Space for Time Series
Han Qiu, Hoang Thanh Lam, Francesco Fusco +1
We propose an approximation algorithm for efficient correlation search in time series data. In our method, we use Fourier transform and neural network to embed time series into a l…
Neural Feature Learning From Relational Database
Hoang Thanh Lam, Tran Ngoc Minh, Mathieu Sinn +2
Feature engineering is one of the most important but most tedious tasks in data science. This work studies automation of feature learning from relational database. We first prove t…
Castor: Contextual IoT Time Series Data and Model Management at Scale
Bei Chen, Bradley Eck, Francesco Fusco +4
We demonstrate Castor, a cloud-based system for contextual IoT time series data and model management at scale. Castor is designed to assist Data Scientists in (a) exploring and ret…
Comparative Analysis of Probabilistic Models for Activity Recognition with an Instrumented Walker
Farheen Omar, Mathieu Sinn, Jakub Truszkowski +3
Rollating walkers are popular mobility aids used by older adults to improve balance control. There is a need to automatically recognize the activities performed by walker users to…
Estimation of ordinal pattern probabilities in fractional Brownian motion
Mathieu Sinn, Karsten Keller
For equidistant discretizations of fractional Brownian motion (fBm), the probabilities of ordinal patterns of order d=2 are monotonically related to the Hurst parameter H. By plugg…
Automated Image Data Preprocessing with Deep Reinforcement Learning
Tran Ngoc Minh, Mathieu Sinn, Hoang Thanh Lam +1
Data preparation, i.e. the process of transforming raw data into a format that can be used for training effective machine learning models, is a tedious and time-consuming task. For…
Towards an Accountable and Reproducible Federated Learning: A FactSheets Approach
Nathalie Baracaldo, Ali Anwar, Mark Purcell +8
Federated Learning (FL) is a novel paradigm for the shared training of models based on decentralized and private data. With respect to ethical guidelines, FL is promising regarding…
Non-parametric estimation of Jensen-Shannon Divergence in Generative Adversarial Network training
Mathieu Sinn, Ambrish Rawat
Generative Adversarial Networks (GANs) have become a widely popular framework for generative modelling of high-dimensional datasets. However their training is well-known to be diff…
The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models
Ambrish Rawat, Killian Levacher, Mathieu Sinn
Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manif…
DLPFS: The Data Leakage Prevention FileSystem
Stefano Braghin, Marco Simioni, Mathieu Sinn
Shared folders are still a common practice for granting third parties access to data files, regardless of the advances in data sharing technologies. Services like Google Drive, Dro…