Related papers: State-of-the-art optical-based physical adversaria…
Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the models into predicting incorrect classes. Our study of major…
We show that the representation of an image in a deep neural network (DNN) can be manipulated to mimic those of other natural images, with only minor, imperceptible perturbations to the original image. Previous methods for generating…
Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…
Adversarial images are samples that are intentionally modified to deceive machine learning systems. They are widely used in applications such as CAPTHAs to help distinguish legitimate human users from bots. However, the noise introduced…
Deep reinforcement learning (DRL) is vulnerable to adversarial perturbations. Adversaries can mislead the policies of DRL agents by perturbing the state of the environment observed by the agents. Existing attacks are feasible in principle,…
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.…
Anomaly detection in videos is an important computer vision problem with various applications including automated video surveillance. Although adversarial attacks on image understanding models have been heavily investigated, there is not…
With the ubiquitous diffusion of social networks, images are becoming a dominant and powerful communication channel. Not surprisingly, they are also increasingly subject to manipulations aimed at distorting information and spreading fake…
Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…
While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…
Over the last few years, convolutional neural networks (CNNs) have proved to reach super-human performance in visual recognition tasks. However, CNNs can easily be fooled by adversarial examples, i.e., maliciously-crafted images that force…
Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…
Complex autonomous control systems are subjected to sensor failures, cyber-attacks, sensor noise, communication channel failures, etc. that introduce errors in the measurements. The corrupted information, if used for making decisions, can…
Deep learning models are used in safety-critical tasks such as automated driving and face recognition. However, small perturbations in the model input can significantly change the predictions. Adversarial attacks are used to identify small…
Physical adversarial attacks pose a significant practical threat as it deceives deep learning systems operating in the real world by producing prominent and maliciously designed physical perturbations. Emphasizing the evaluation of…
Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…
Universal Adversarial Perturbations (UAPs) are imperceptible, image-agnostic vectors that cause deep neural networks (DNNs) to misclassify inputs with high probability. In practical attack scenarios, adversarial perturbations may undergo…
Adversarial attacks dramatically change the output of an otherwise accurate learning system using a seemingly inconsequential modification to a piece of input data. Paradoxically, empirical evidence indicates that even systems which are…
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…
We find that images contain intrinsic structure that enables the reversal of many adversarial attacks. Attack vectors cause not only image classifiers to fail, but also collaterally disrupt incidental structure in the image. We demonstrate…