Search

While deep learning models are thought to be resistant to random perturbations, it has been demonstrated that these architectures are vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These vulnerabilities make it challenging to deploy Deep Neural Network (DNN) models in security-critical areas. Recently, many research studies have been conducted to develop defense techniques enabling more robust models. In this paper, we target detecting adversarial samples by differentiating them from their clean equivalents. We investigate various metrics for detecting adversarial samples. We first leverage moment-based predictive uncertainty estimates of DNN classifiers derived through Monte-Carlo (MC) Dropout Sampling. We also introduce a new method that operates in the subspace of deep features obtained by the model. We verified the effectiveness of our approach on different datasets. Our experiments show that these approaches complement each other, and combined usage of all metrics yields 99 % ROC-AUC adversarial detection score for well-known attack algorithms. [ABSTRACT FROM AUTHOR]

Today, incorporating advanced machine learning techniques into intrusion detection systems (IDSs) plays a crucial role in securing mobile edge computing systems. However, the mobility demands of our modern society require more advanced IDSs to make a good trade-off between coping with the rapid growth of traffic data and responding to attacks. Thus, in this paper, we propose a lightweight distributed IDS that exploits the advantages of centralized platforms to train and learn from large amounts of data. We investigate the benefits of two promising bio-inspired optimization algorithms, namely Ant Lion Optimization and Ant Colony Optimization, to find the optimal data representation for the classification process. We use Deep Forest as a classifier to detect intrusive actions more robustly and generate as few false positives as possible. The experiment results show that the proposed approach can enhance the reliability of lightweight intrusion detection systems in terms of accuracy and execution time. [Display omitted] • Hybrid learning model has benefits in supporting intrusion detection in mobile edge computing. • Deep Forest is effective in strengthening attack detection predictability of IDSs in mobile edge computing. • Bio-inspired optimization algorithms improve the classification process. • The employed strategy enhances attack recognition of IDSs to deal with different threats in mobile edge computing. [ABSTRACT FROM AUTHOR]

• The combination of mobile devices and edge computing reduces the total computing overhead and makes resource allocation reasonable. • Evaluate system performance by the weighted sum of delay and energy consumption. • Change the parameter update method to accelerate the convergence speed of the deep reinforcement learning algorithm. • A neural network is used to approximate the behavior value function, and a target q network is used to update the target. With the arrival of the 5th generation mobile networks (5 G) era, the data needed by mobile devices (MDs) is explosively growing. High-consumption, low-latency applications are huge challenges for resource-constrained Internet of things (IoT) devices. Mobile edge computing overcomes the limitations of computing resources on MDs by offloading tasks generated by MDs and assigning them to nearby MEC servers. Therefore, mobile edge computing (MEC) becomes important. This paper presents a task offloading strategy for the multi-device multi-server system. To meet the task requirements of different MDs, we formulate an overhead minimization problem to optimize the delay and energy consumption of the system. We propose the Double Deep Q Network (Double-DQN) algorithm to perform location selection strategies for tasks generated on the mobile devices and allocate respective computing resources. Simulation results show that the algorithm can allocate resources reasonably and reduce the overhead of the entire system. [Display omitted] [ABSTRACT FROM AUTHOR]