Related papers: Breaking Boundaries: Balancing Performance and Rob…

This chapter introduces and investigates some fundamental questions on the relationship between accuracy and robustness in both classical and quantum classification algorithms under noisy and adversarial conditions. We introduce and clarify…

In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as…

Future wireless networks powered by renewable energy sources and storage systems (e.g., batteries) require energy-aware mechanisms to ensure stability in critical and high-demand scenarios. These include large-scale user gatherings,…

We consider a distributed edge computing scenario consisting of several wireless nodes that are located over an area of interest. Specifically, some of the "master" nodes are tasked to sense the environment (e.g., by acquiring images or…

Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be…

Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their…

Deep learning models are increasingly deployed in safety-critical tasks where predictions must satisfy hard constraints, such as physical laws, fairness requirements, or safety limits. However, standard architectures lack built-in…

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Decentralized optimization is typically studied under the assumption of noise-free transmission. However, real-world scenarios often involve the presence of noise due to factors such as additive white Gaussian noise channels or…

Motivated by the superior performance of deep learning in many applications including computer vision and natural language processing, several recent studies have focused on applying deep neural network for devising future generations of…

Fairness in machine learning has attracted increasing attention in recent years. The fairness methods improving algorithmic fairness for in-distribution data may not perform well under distribution shifts. In this paper, we first…

The reliability of a learning model is key to the successful deployment of machine learning in various applications. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. It…

Group distributionally robust optimization, which aims to improve robust accuracies -- worst-group and unbiased accuracies -- is a prominent algorithm used to mitigate spurious correlations and address dataset bias. Although existing…

Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed compare-and-contrast of the latest proposals to understand what…

As adversarial attacks against machine learning models have raised increasing concerns, many denoising-based defense approaches have been proposed. In this paper, we summarize and analyze the defense strategies in the form of symmetric…

Deep Neural Networks (DNNs) have revolutionized a wide range of industries, from healthcare and finance to automotive, by offering unparalleled capabilities in data analysis and decision-making. Despite their transforming impact, DNNs face…

Decentralized optimization with time-varying networks is an emerging paradigm in machine learning. It saves remarkable communication overhead in large-scale deep training and is more robust in wireless scenarios especially when nodes are…

Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work…

Despite the rich literature on scheduling algorithms for wireless networks, algorithms that can provide deadline guarantees on packet delivery for general traffic and interference models are very limited. In this paper, we study the problem…

The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending attacks constrained within low magnitude Lp norm bounds,…