Related papers: Catastrophic Overfitting: A Potential Blessing in …
Adversarial training is often formulated as a min-max problem, however, concentrating only on the worst adversarial examples causes alternating repetitive confusion of the model, i.e., previously defended or correctly classified samples are…
Adversarial training has achieved remarkable advancements in defending against adversarial attacks. Among them, fast adversarial training (FAT) is gaining attention for its ability to achieve competitive robustness with fewer computing…
This paper examines the phenomenon of probabilistic robustness overestimation in TRADES, a prominent adversarial training method. Our study reveals that TRADES sometimes yields disproportionately high PGD validation accuracy compared to the…
Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…
It is common practice in deep learning to use overparameterized networks and train for as long as possible; there are numerous studies that show, both theoretically and empirically, that such practices surprisingly do not unduly harm the…
In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on the challenge of…
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are…
Adversarial training (AT) is an effective technique for enhancing adversarial robustness, but it usually comes at the cost of a decline in generalization ability. Recent studies have attempted to use clean training to assist adversarial…
We show that label noise exists in adversarial training. Such label noise is due to the mismatch between the true label distribution of adversarial examples and the label inherited from clean examples - the true label distribution is…
Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…
Privacy and security concerns in real-world applications have led to the development of adversarially robust federated models. However, the straightforward combination between adversarial training and federated learning in one framework can…
Deep neural networks are widely used in various fields because of their powerful performance. However, recent studies have shown that deep learning models are vulnerable to adversarial attacks, i.e., adding a slight perturbation to the…
Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of…
In safety-critical applications such as medical imaging and autonomous driving, where decisions have profound implications for patient health and road safety, it is imperative to maintain both high adversarial robustness to protect against…
Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…
Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust…
Our goal is to understand why the robustness drops after conducting adversarial training for too long. Although this phenomenon is commonly explained as overfitting, our analysis suggest that its primary cause is perturbation underfitting.…
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models. However, it is conservative or even pessimistic so that it sometimes hurts the natural generalization. In this paper,…
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce…