Concept
Adversarial machine learning
Publications associées (242)
Efficient local linearity regularization to overcome catastrophic overfitting
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora
Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...
2024Revisiting Character-level Adversarial Attacks for Language Models
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu, Elias Abad Rocamora
Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...
2024Understanding 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 ...
EPFL2024MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning
Alexandre Massoud Alahi, Mohamed Ossama Ahmed Abdelfattah, Mariam Ahmed Mahmoud Hegazy Hassan
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 ...
2024Robust NAS under adversarial training: benchmark, theory, and beyond
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu
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 ...
2024Can Gas Consumption Data Improve the Performance of Electricity Theft Detection?
Machine learning techniques have been extensively developed in the field of electricity theft detection. However, almost all typical models primarily rely on electricity consumption data to identify fraudulent users, often neglecting other pertinent househ ...
Ieee-Inst Electrical Electronics Engineers Inc2024Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning
Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...
EPFL2024Residual-based attention in physics-informed neural networks
Nikolaos Stergiopoulos, Sokratis Anagnostopoulos
Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...
Lausanne2024Robust machine learning for neuroscientific inference
Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...
EPFL2024