Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms. Adversarial training is one of the methods used to defend against the threat of adversarial attacks. It is a training schema that utilizes an alternative objective function to provide model generalization for both adversarial data and clean data. In this systematic review, we focus particularly on adversarial training as a method of improving the defensive capacities and robustness of machine learning models. Specifically, we focus on adversarial sample accessibility through adversarial sample generation methods. The purpose of this systematic review is to survey state-of-the-art adversarial training and robust optimization methods to identify the research gaps within this field of applications. The literature search was conducted using Engineering Village (Engineering Village is an engineering literature search tool, which provides access to 14 engineering literature and patent databases), where we collected 238 related papers. The papers were filtered according to defined inclusion and exclusion criteria, and information was extracted from these papers according to a defined strategy. A total of 78 papers published between 2016 and 2021 were selected. Data were extracted and categorized using a defined strategy, and bar plots and comparison tables were used to show the data distribution. The findings of this review indicate that there are limitations to adversarial training methods and robust optimization. The most common problems are related to data generalization and overfitting.

No abstract

No abstract

Network–wide broadcasting is used extensively in mobile ad hoc networks for route discovery and for disseminating data throughout the network. Flooding is a common approach to performing network-wide broadcasting. Although it is a simple mechanism that can achieve high delivery ratio, flooding consumes much of the communication bandwidth and causes serious packet redundancy, contention and collision. In this paper, the authors propose new broadcast schemes that reduce the overhead associated with flooding. In these schemes, a node selects a subset of its neighbors for forwarding the packet being broadcast to additional nodes. The selection process has for goal reducing the number of neighbors and maximizing the number of nodes that they can reach (i.e., forward the packet to). By applying this novel neighborhood-based broadcasting strategy, the authors have come up with routing protocols that have very low overhead. These protocols were implemented and simulated within the GloMoSim 2.03 network simulator. The simulation experiments show that our routing protocols can reduce the overhead for both low and high mobility substantially, as compared with the well-known and promising AODV routing protocol. In addition, they outperform AODV by increasing the delivery ratio and decreasing the end-to-end delays of data packets.

No abstract