With the imminent large-scale deployment of 5G and the emergence of 6G research, there is an increased interest in understanding the propagation channels for the bands from 10-1000 GHz, which will play a vital role in those systems. This talk will first review some propagation basics, and then present a number of recent results in the measurement and deterministic simulation of such channels, with an emphasis will be on double-directional and/or dynamic channel characteristics. We will discuss, among other aspects, how different streets have different pathloss coefficients, how passing cars alternate between being reflectors and blockers, how trees and other objects near windows critically impact outdoor-to-indoor propagation, and that some first THz measurements indicate surprisingly large angular dispersion. A discussion on how to model all these effects, and how they impact system performance, will round off the tutorial.

Breakthroughs in machine learning (ML) and particularly deep learning have transformed every aspects of our lives from face recognition, medical diagnosis, and natural language processing. This progress has been fueled mainly by the availability of more data and more computing power. However, the current premise in classical ML is based on a single node in a centralized and remote data center with full access to a global dataset and a massive amount of storage and computing. Nevertheless, the advent of a new breed of intelligent devices ranging from drones to self-driving vehicles, makes cloud-based ML inadequate. This talk will present the vision of distributed edge intelligence featuring key enablers, architectures, algorithms and some recent results.

Federated learning, as a promising machine learning approach, has emerged to leverage a distributed personalized dataset from a number of nodes, e.g., mobile devices, to improve performance while simultaneously providing privacy preservation for mobile users. In the federated learning, training data is widely distributed and maintained on the mobile devices as workers. A central aggregator updates a global model by collecting local updates from mobile devices using their local training data to train the global model in each iteration. However, unreliable data may be uploaded by the mobile devices (i.e., workers), leading to frauds in tasks of federated learning. The workers may perform unreliable updates intentionally, e.g., the data poisoning attack, or unintentionally, e.g., low-quality data caused by energy constraints or high-speed mobility. Therefore, finding out trusted and reliable workers in federated learning tasks becomes critical. In this talk, the concept of reputation is introduced as a metric. Based on this metric, a reliable worker selection scheme is proposed for federated learning tasks. Consortium blockchain is leveraged as a decentralized approach for achieving efficient reputation management of the workers without repudiation and tampering. The proposed approach is demonstrated to improve the reliability of federated learning tasks in mobile networks.

The recent rapid advances in machine and deep learning algorithms have found many applications in the security space, targeting various applications including intrusion detection systems, malware detection, and attribution. Despite their extraordinary superhuman performance in various tasks, machine learning algorithms are prone to adversarial examples, carefully crafted input examples to the machine algorithms that will result in fooling the machine algorithms by, for example, reducing their confidence or even resulting in misclassification. In this talk, we review advances in adversarial machine learning space as it pertain to various application security tasks. We further highlight and review several recent studies to demonstrate the success of adversarial examples on various applications, including website fingerprinting, malicious binaries classification, source code authorship identification, and intrusion detection systems. We discuss various defenses and conclude with open directions.