Related papers: Fighting Gradients with Gradients: Dynamic Defense…
Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which…
Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…
Many defenses against adversarial attacks (\eg robust classifiers, randomization, or image purification) use countermeasures put to work only after the attack has been crafted. We adopt a different perspective to introduce $A^5$…
Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although backdoor mitigation has been studied extensively for image…
Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing…
In this paper, we study fast training of adversarially robust models. From the analyses of the state-of-the-art defense method, i.e., the multi-step adversarial training, we hypothesize that the gradient magnitude links to the model…
In recent years, Deep Neural Network models have been developed in different fields, where they have brought many advances. However, they have also started to be used in tasks where risk is critical. A misdiagnosis of these models can lead…
Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications. Recently, however, DNNs are shown to be vulnerable to adversarial example attacks with slight perturbations on the inputs.…
In this paper, we study the problem of how to defend classifiers against adversarial attacks that fool the classifiers using subtly modified input data. In contrast to previous works, here we focus on the white-box adversarial defense where…
Deep learning classifiers are now known to have flaws in the representations of their class. Adversarial attacks can find a human-imperceptible perturbation for a given image that will mislead a trained model. The most effective methods to…
While deep neural networks have achieved remarkable success in various computer vision tasks, they often fail to generalize to new domains and subtle variations of input images. Several defenses have been proposed to improve the robustness…
Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to…
Improving the resistance of deep neural networks against adversarial attacks is important for deploying models to realistic applications. However, most defense methods are designed to defend against intensity perturbations and ignore…
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show…
Deep models are highly susceptible to adversarial attacks. Such attacks are carefully crafted imperceptible noises that can fool the network and can cause severe consequences when deployed. To encounter them, the model requires training…
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input…
Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…
Transfer-based adversarial attacks raise a severe threat to real-world deep learning systems since they do not require access to target models. Adversarial training (AT), which is recognized as the strongest defense against white-box…
Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries…
We experimented with front-end enhanced neural models where a differentiable and fully convolutional model with a skip connection is added before a frozen backbone classifier. By training such composite models using a small learning rate…