Related papers: Mitigating Error Amplification in Fast Adversarial…
The distributionally robust optimization (DRO)-based graph neural network methods improve recommendation systems' out-of-distribution (OOD) generalization by optimizing the model's worst-case performance. However, these studies fail to…
Generative Adversarial Networks (GANs) are the most popular image generation models that have achieved remarkable progress on various computer vision tasks. However, training instability is still one of the open problems for all GAN-based…
Deep Neural Networks (DNNs) are known to be vulnerable to various adversarial perturbations. To address the safety concerns arising from these vulnerabilities, adversarial training (AT) has emerged as one of the most effective paradigms for…
Fast adversarial training (FAT) aims to enhance the robustness of models against adversarial attacks with reduced training time, however, FAT often suffers from compromised robustness due to insufficient exploration of adversarial space. In…
Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training approaches lies in their reliance on a fixed perturbation budget,…
Despite the success of convolutional neural networks (CNNs) in many academic benchmarks for computer vision tasks, their application in the real-world is still facing fundamental challenges. One of these open problems is the inherent lack…
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…
Adversarial attacks and robustness in Deep Reinforcement Learning (DRL) have been widely studied in various threat models; however, few consider environmental state perturbations, which are natural in embodied scenarios. To improve the…
Assigning importance weights to adversarial data has achieved great success in training adversarially robust networks under limited model capacity. However, existing instance-reweighted adversarial training (AT) methods heavily depend on…
Up to now, the training processes of typical Generative Adversarial Networks (GANs) are still particularly sensitive to data properties and hyperparameters, which may lead to severe oscillations, difficulties in convergence, or even…
Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…
Adversarial training and its many variants substantially improve deep network robustness, yet at the cost of compromising standard accuracy. Moreover, the training process is heavy and hence it becomes impractical to thoroughly explore the…
There has been a recent surge in single-step adversarial training as it shows robustness and efficiency. However, a phenomenon referred to as ``catastrophic overfitting" has been observed, which is prevalent in single-step defenses and may…
Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…
Adversarial training is a defense method that trains machine learning models on intentionally perturbed attack inputs, so they learn to be robust against adversarial examples. This paper develops a robust voltage control framework for…
Data augmentation plays a pivotal role in enhancing and diversifying training data. Nonetheless, consistently improving model performance in varied learning scenarios, especially those with inherent data biases, remains challenging. To…
Adversarial training (AT) is one of the most effective strategies for promoting model robustness. However, recent benchmarks show that most of the proposed improvements on AT are less effective than simply early stopping the training…
In this paper, we investigate on improving the adversarial robustness obtained in adversarial training (AT) via reducing the difficulty of optimization. To better study this problem, we build a novel Bregman divergence perspective for AT,…
Federated learning (FL) faces critical challenges, particularly in heterogeneous environments where non-independent and identically distributed data across clients can lead to unfair and inefficient model performance. In this work, we…
Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robust accuracy against adversarial attacks suddenly and…