Publication
Constructing a provably adversarially-robust classifier from a high accuracy one
Publications associées (33)
Understanding generalization and robustness in modern deep learning
In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...
EPFL2024Towards Robust Monitoring of the Laser Powder Bed Fusion Process based on Acoustic Emission combined with Machine Learning Solutions
Laser Powder Bed Fusion (LPBF) is an Additive Manufacturing (AM) process consolidating parts layer by layer, from a metallic powder bed. It allows no limitation in terms of geometry and is therefore of particular interest to various industries. Metallic LP ...
EPFL2023Estimating and Improving the Robustness of Attributions in Text
End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...
EPFL2023Robustness and invariance properties of image classifiers
Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...
EPFL2022Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.
In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning.However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...
EPFL2022On the robustness of randomized classifiers to adversarial examples
This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (i.e. classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of statistical learning theo ...
SPRINGER2022Classification of fall directions via wearable motion sensors
Effective fall-detection and classification systems are vital in mitigating severe medical and economical consequences of falls to people in the fall risk groups. One class of such systems is based on wearable sensors. While there is a vast amount of acade ...
ACADEMIC PRESS INC ELSEVIER SCIENCE2022Predicting Superagers by Machine Learning Classification Based on the Functional Brain Connectome Using Resting-State Functional Magnetic Resonance Imaging
Superagers are defined as older adults who have youthful memory performance comparable to that of middle-aged adults. Classifying superagers based on the brain connectome using machine learning modeling can provide important insights on the physiology unde ...
OXFORD UNIV PRESS INC2021Unsupervised Domain Adaptation for Cross-Subject Few-Shot Neurological Symptom Detection
Modern machine learning tools have shown promise in detecting symptoms of neurological disorders. However, current approaches typically train a unique classifier for each subject. This subject-specific training scheme requires long labeled recordings from ...
IEEE2021Network Classifiers Based On Social Learning
Ali H. Sayed, Stefan Vlaski, Virginia Bordignon
This work proposes a new way of combining independently trained classifiers over space and time. Combination over space means that the outputs of spatially distributed classifiers are aggregated. Combination over time means that the classifiers respond to ...
IEEE2021