Related papers: Detecting Adversarial Samples Using Density Ratio …
Adversarial attacks have received increasing attention and it has been widely recognized that classical DNNs have weak adversarial robustness. The most commonly used adversarial defense method, adversarial training, improves the adversarial…
Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…
Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method…
Learning-enabled components (LECs) are widely used in cyber-physical systems (CPS) since they can handle the uncertainty and variability of the environment and increase the level of autonomy. However, it has been shown that LECs such as…
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…
Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…
Research on developing deep learning techniques for autonomous spacecraft relative navigation challenges is continuously growing in recent years. Adopting those techniques offers enhanced performance. However, such approaches also introduce…
Generative adversarial networks (GANs) are able to model the complex highdimensional distributions of real-world data, which suggests they could be effective for anomaly detection. However, few works have explored the use of GANs for the…
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a…
Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…
As the number and complexity of malware attacks continue to increase, there is an urgent need for effective malware detection systems. While deep learning models are effective at detecting malware, they are vulnerable to adversarial…
We present a method for adversarial attack detection based on the inspection of a sparse set of neurons. We follow the hypothesis that adversarial attacks introduce imperceptible perturbations in the input and that these perturbations…
Adversarially robust learning aims to design algorithms that are robust to small adversarial perturbations on input variables. Beyond the existing studies on the predictive performance to adversarial samples, our goal is to understand…
Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples,…
Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g.…
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial…
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can…
Deep computer vision systems being vulnerable to imperceptible and carefully crafted noise have raised questions regarding the robustness of their decisions. We take a step back and approach this problem from an orthogonal direction. We…
We introduce an adversarial sample detection algorithm based on image residuals, specifically designed to guard against patch-based attacks. The image residual is obtained as the difference between an input image and a denoised version of…
The renaissance of deep learning has led to the massive development of automated driving. However, deep neural networks are vulnerable to adversarial examples. The perturbations of adversarial examples are imperceptible to human eyes but…