Related papers: Fast Gradient Non-sign Methods

Crafting adversarial examples for the transfer-based attack is challenging and remains a research hot spot. Currently, such attack methods are based on the hypothesis that the substitute model and the victim model learn similar decision…

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a…

The notion of adversarial attacks on image classification models based on convolutional neural networks (CNN) is introduced in this work. To classify images, deep learning models called CNNs are frequently used. However, when the networks…

Despite the huge success of Deep Neural Networks (DNNs) in a wide spectrum of machine learning and data mining tasks, recent research shows that this powerful tool is susceptible to maliciously crafted adversarial examples. Up until now,…

Sign Gradient Descent (SignGD) is a simple yet robust optimization method, widely used in machine learning for its resilience to gradient noise and compatibility with low-precision computations. While its empirical performance is well…

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample.…

Neural retrieval models have acquired significant effectiveness gains over the last few years compared to term-based methods. Nevertheless, those models may be brittle when faced to typos, distribution shifts or vulnerable to malicious…

Like Graph Neural Networks (GNNs), Signed Graph Neural Networks (SGNNs) are also up against fairness issues from source data and typical aggregation method. In this paper, we are pioneering to make the investigation of fairness in SGNNs…

Deep learning achieves state-of-the-art performance in many tasks but exposes to the underlying vulnerability against adversarial examples. Across existing defense techniques, adversarial training with the projected gradient decent attack…

Recent research has proved that deep neural networks (DNNs) are vulnerable to adversarial examples, the legitimate input added with imperceptible and well-designed perturbations can fool DNNs easily in the testing stage. However, most of…

Graph Neural Networks (GNNs) have received significant attention due to their state-of-the-art performance on various graph representation learning tasks. However, recent studies reveal that GNNs are vulnerable to adversarial attacks, i.e.…

Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…

Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversarial examples via a first-order method like projected gradient…

It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate…

The nature of deep neural networks has given rise to a variety of attacks, but little work has been done to address the effect of adversarial attacks on segmentation models trained on MRI datasets. In light of the grave consequences that…

Neural networks have demonstrated remarkable success in learning and solving complex tasks in a variety of fields. Nevertheless, the rise of those networks in modern computing has been accompanied by concerns regarding their vulnerability…

Fast gradient sign attack series are popular methods that are used to generate adversarial examples. However, most of the approaches based on fast gradient sign attack series cannot balance the indistinguishability and transferability due…

Android malware has become an increasingly critical threat to organizations, society and individuals, posing significant risks to privacy, data security and infrastructure. As malware continues to evolve in terms of complexity and…

Black-box query attacks, which rely only on the output of the victim model, have proven to be effective in attacking deep learning models. However, existing black-box query attacks show low performance in a novel scenario where only a few…

Deep learning models are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on benign inputs. However, under the black-box setting, most existing adversaries often have a poor transferability to attack…