Optimism in the Face of Adversity: Understanding and Improving Deep Learning Through Adversarial Robustness

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

In recent years, neural quantum states have emerged as a powerful variational approach, achieving state-of-the-art accuracy when representing the ground-state wave function of a great variety of quantum many-body systems, including spin lattices, interacti ...

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

Neurons in the human amygdala and hippocampus are classically thought to encode a person’s identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semanti ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

Rigid body interactions are fundamental to numerous scientific disciplines, but remain challenging to simulate due to their abrupt nonlinear nature and sensitivity to complex, often unknown environmental factors. These challenges call for adaptable learnin ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

FDTD/FEM simulations, strengthened by machine learning, achieve 95.44% optical absorption efficiency in TiO 2 /TiN plasmonic nanocavities for solar energy harvesting. ...

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and req ...

Current transformer-based skeletal action recognition models tend to focus on a limited set of joints and low-level motion patterns to predict action classes. This results in significant performance degradation under small skeleton perturbations or changin ...

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 ...

This paper introduces MNE-RT, a Python package designed for real-time neural feature extraction from magne-toencephalography (MEG) and electroencephalography (EEG) signals in Brain-Computer Interface (BCI) systems. The package incorporates efficient algori ...

Deep learning has revolutionized the field of computer vision, a success largely attributable to the growing size of models, datasets, and computational power. Simultaneously, a critical pain point arises as several computer vision applications are deploye ...

This thesis explores the how computational methods can be used to enrich the history of architecture. Using Venice as a case study, it establishes a rich and multifaceted information system, made up of temporal, stylistic, photographic, architectural, and ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Modern computing has enhanced our understanding of how social interactions shape collective behaviour in animal societies. Although analytical models dominate in studying collective behaviour, this study introduces a deep learning model to assess social in ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

Optimism in the Face of Adversity: Understanding and Improving Deep Learning Through Adversarial Robustness

Chat with Graph Search

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Accurate neural quantum states for interacting lattice bosons

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

Machine Learning for Modeling Stock Returns

Integrating Physics and Topology in Neural Networks for Learning Rigid Body Dynamics

Aggregating Spatial and Photometric Context for Photometric Stereo

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Machine-learning-empowered FDTD/FEM simulations for predictive solar energy absorption in plasmonic metamaterial nanocavity arrays

Self-supervised and few-shot learning for robust bioaerosol monitoring

MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Understanding generalization and robustness in modern deep learning

Advances on Real Time M/EEG Neural Feature Extraction

Fast and Future: Towards Efficient Forecasting in Video Semantic Segmentation

The Skin of Venice: A Computational Approach to the City's Urban Structure

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Predicting the long-term collective behaviour of fish pairs with deep learning

Robust NAS under adversarial training: benchmark, theory, and beyond