相关论文: MixUp as Directional Adversarial Training

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…

Despite impressive success in many tasks, deep learning models are shown to rely on spurious features, which will catastrophically fail when generalized to out-of-distribution (OOD) data. Invariant Risk Minimization (IRM) is proposed to…

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…

The recent advances in deep transfer learning reveal that adversarial learning can be embedded into deep networks to learn more transferable features to reduce the distribution discrepancy between two domains. Existing adversarial domain…

Intrinsic susceptibility of deep learning to adversarial examples has led to a plethora of attack techniques with a broad common objective of fooling deep models. However, we find slight compositional differences between the algorithms…

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced learning. Instead of learning a mixture model directly from a…

We present a simple yet effective Targeted Adversarial Training (TAT) algorithm to improve adversarial training for natural language understanding. The key idea is to introspect current mistakes and prioritize adversarial training steps to…

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Due to numerous breakthroughs in real-world applications brought by machine intelligence, deep neural networks (DNNs) are widely employed in critical applications. However, predictions of DNNs are easily manipulated with imperceptible…

The current Air Traffic Management (ATM) system worldwide has reached its limits in terms of predictability, efficiency and cost effectiveness. Different initiatives worldwide propose trajectory-oriented transformations that require high…

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Many previous proposals for adversarial training of deep neural nets have included di- rectly modifying the gradient, training on a mix of original and adversarial examples, using contractive penalties, and approximately optimizing…

Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen…

Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have…

Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial training and its variants have been shown to be the most…

Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input transformation attacks. However, these methods originally…

Deep neural networks (DNNs) are susceptible to universal adversarial perturbations (UAPs). These perturbations are meticulously designed to fool the target model universally across all sample classes. Unlike instance-specific adversarial…

Though deep neural networks exhibit superior performance on various tasks, they are still plagued by adversarial examples. Adversarial training has been demonstrated to be the most effective method to defend against adversarial attacks.…

Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…