Related papers: Higher-Order Adversarial Patches for Real-Time Obj…

Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold hypothesis posits, high-dimensional data tends to be part…

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge…

The advent of convenient and efficient fully unmanned stores equipped with artificial intelligence-based automated checkout systems marks a new era in retail. However, these systems have inherent artificial intelligence security…

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

In the future, powerful AI systems may be deployed in high-stakes settings, where a single failure could be catastrophic. One technique for improving AI safety in high-stakes settings is adversarial training, which uses an adversary to…

It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching adversarial patches to real objects. However, most of the existing…

Machine learning has witnessed tremendous growth in its adoption and advancement in the last decade. The evolution of machine learning from traditional algorithms to modern deep learning architectures has shaped the way today's technology…

Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result. The vulnerability has led to a surge of research in this direction, including adversarial…

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on…

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…

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

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…

Monocular 3D object detection plays a pivotal role in the field of autonomous driving and numerous deep learning-based methods have made significant breakthroughs in this area. Despite the advancements in detection accuracy and efficiency,…

Due to their performance and simplicity, rigid body simulators are often used in applications where the objects of interest can considered very stiff. However, no material has infinite stiffness, which means there are potentially cases…

With the rapid development of deep learning, object detectors have demonstrated impressive performance; however, vulnerabilities still exist in certain scenarios. Current research exploring the vulnerabilities using adversarial patches…

Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious security concerns…

New transformer networks have been integrated into object tracking pipelines and have demonstrated strong performance on the latest benchmarks. This paper focuses on understanding how transformer trackers behave under adversarial attacks…

Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness,…