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 some geomet
ric consequences of adversarial training on the decision boundary of deep networks give an edge to certain types of black-box attacks. In particular, we define a metric called robustness gain to show that while adversarial training is an effective method to dramatically improve the robustness in white-box scenarios, it may not provide such a good robustness gain against the more realistic decision-based black-box attacks. Moreover, we show that even the minimal perturbation white-box attacks can converge faster against adversarially-trained neural networks compared to the regular ones.
Modern neural networks have been successful in many regression-based tasks such as face recognition, facial landmark detection, and image generation. In this work, we investigate an intuitive but understudied characteristic of modern neural networks,
namely, the nonsmoothness. The experiments using synthetic data confirm that such operations as ReLU and max pooling in modern neural networks lead to nonsmoothness. We quantify the nonsmoothness using a feature named the sum of the magnitude of peaks (SMP) and model the input-output relationships for building blocks of modern neural networks. Experimental results confirm that our model can accurately predict the statistical behaviors of the nonsmoothness as it propagates through such building blocks as the convolutional layer, the ReLU activation, and the max pooling layer. We envision that the nonsmoothness feature can potentially be used as a forensic tool for regression-based applications of neural networks.
In federated learning (FL), reducing the communication overhead is one of the most critical challenges since the parameter server and the mobile devices share the training parameters over wireless links. With such consideration, we adopt the idea of
SignSGD in which only the signs of the gradients are exchanged. Moreover, most of the existing works assume Channel State Information (CSI) available at both the mobile devices and the parameter server, and thus the mobile devices can adopt fixed transmission rates dictated by the channel capacity. In this work, only the parameter server side CSI is assumed, and channel capacity with outage is considered. In this case, an essential problem for the mobile devices is to select appropriate local processing and communication parameters (including the transmission rates) to achieve a desired balance between the overall learning performance and their energy consumption. Two optimization problems are formulated and solved, which optimize the learning performance given the energy consumption requirement, and vice versa. Furthermore, considering that the data may be distributed across the mobile devices in a highly uneven fashion in FL, a stochastic sign-based algorithm is proposed. Extensive simulations are performed to demonstrate the effectiveness of the proposed methods.
We consider the relaying application of unmanned aerial vehicles (UAVs), in which UAVs are placed between two transceivers (TRs) to increase the throughput of the system. Instead of studying the placement of UAVs as pursued in existing literature, we
focus on investigating the placement of a jammer or a major source of interference on the ground to effectively degrade the performance of the system, which is measured by the maximum achievable data rate of transmission between the TRs. We demonstrate that the optimal placement of the jammer is in general a non-convex optimization problem, for which obtaining the solution directly is intractable. Afterward, using the inherent characteristics of the signal-to-interference ratio (SIR) expressions, we propose a tractable approach to find the optimal position of the jammer. Based on the proposed approach, we investigate the optimal positioning of the jammer in both dual-hop and multi-hop UAV relaying settings. Numerical simulations are provided to evaluate the performance of our proposed method.
We consider unmanned aerial vehicle (UAV)-assisted wireless communication employing UAVs as relay nodes to increase the throughput between a pair of transmitter and receiver. We focus on developing effective methods to position the UAV(s) in the sky
in the presence of interference in the environment, the existence of which makes the problem non-trivial and our methodology different from the current art. We study the optimal position planning, which aims to maximize the (average) signal-to-interference-ratio (SIR) of the system, in the presence of: i) one major source of interference, ii) stochastic interference. For each scenario, we first consider utilizing a single UAV in the dual-hop relay mode and determine its optimal position. Afterward, multiple UAVs in the multi-hop relay mode are considered, for which we investigate two novel problems concerned with determining the optimal number of required UAVs and developing an optimal fully distributed position alignment method. Subsequently, we propose a cost-effective method that simultaneously minimizes the number of UAVs and determines their optimal positions to guarantee a certain (average) SIR of the system. Alternatively, for a given number of UAVs, we develop a fully distributed placement algorithm along with its performance guarantee. Numerical simulations are provided to evaluate the performance of our proposed methods.
Vehicular ad-hoc networks (VANETs) have recently attracted a lot of attention due to their immense potentials and applications. Wide range of coverage and accessibility to end users make VANETs a good target for commercial companies. In this paper, w
e consider a scenario in which advertising companies aim to disseminate their advertisements in different areas of a city by utilizing VANETs infrastructure. These companies compete for renting the VANETs infrastructure to spread their advertisements. We partition the city map into different blocks, and consider a manager for all the blocks who is in charge of splitting the time between interested advertising companies. Each advertising company (AdC) is charged proportional to the allocated time. In order to find the best time splitting between AdCs, we propose a Stackelberg game scheme in which the block manager assigns the companies to the blocks and imposes the renting prices to different companies in order to maximize its own profit. Based on this, AdCs request the amount of time they desire to rent the infrastructure in order to maximize their utilities. To obtain the Stackelberg equilibrium of the game, a mixed integer nonlinear optimization problem is solved using the proposed optimal and sub-optimal algorithms. The simulation results demonstrate that the sub-optimal algorithm approaches the optimal one in performance with lower complexity.
RF-powered backscatter communication is a promising new technology that can be deployed for battery-free applications such as internet of things (IoT) and wireless sensor networks (WSN). However, since this kind of communication is based on the ambie
nt RF signals and battery-free devices, they are vulnerable to interference and jamming. In this paper, we model the interaction between the user and a smart interferer in an ambient backscatter communication network as a game. We design the utility functions of both the user and interferer in which the backscattering time is taken into the account. The convexity of both sub-game optimization problems is proved and the closed-form expression for the equilibrium of the Stackelberg game is obtained. Due to lack of information about the system SNR and transmission strategy of the interferer, the optimal strategy is obtained using the Q-learning algorithm in a dynamic iterative manner. We further introduce hotbooting Q-learning as an effective approach to expedite the convergence of the traditional Q-learning. Simulation results show that our approach can obtain considerable performance improvement in comparison to random and fixed backscattering time transmission strategies and improves the convergence speed of Q-Learning by about 31%.
We consider unmanned aerial vehicle (UAV)-assisted wireless communication employing UAVs as relay nodes to increase the throughput between a pair of transmitter and receiver. We focus on developing effective methods to position the UAV(s) in the sky
in the presence of a major source of interference, the existence of which makes the problem non-trivial. First, we consider utilizing a single UAV, for which we develop a theoretical framework to determine its optimal position aiming to maximize the SIR of the system. To this end, we investigate the problem for three practical scenarios, in which the position of the UAV is: (i) vertically fixed, horizontally adjustable; (ii) horizontally fixed, vertically adjustable; (iii) both horizontally and vertically adjustable. Afterward, we consider employing multiple UAVs, for which we propose a cost-effective method that simultaneously minimizes the number of required UAVs and determines their optimal positions so as to guarantee a certain SIR of the system. We further develop a distributed placement algorithm, which can increase the SIR of the system given an arbitrary number of UAVs. Numerical simulations are provided to evaluate the performance of our proposed methods.
In the era of big-data, the jobs submitted to the clouds exhibit complicated structures represented by graphs, where the nodes denote the sub-tasks each of which can be accommodated at a slot in a server, while the edges indicate the communication co
nstraints among the sub-tasks. We develop a framework for efficient allocation of graph jobs in geo-distributed cloud networks (GDCNs), explicitly considering the power consumption of the datacenters (DCs). We address the following two challenges arising in graph job allocation: i) the allocation problem belongs to NP-hard nonlinear integer programming; ii) the allocation requires solving the NP-complete sub-graph isomorphism problem, which is particularly cumbersome in large-scale GDCNs. We develop a suite of efficient solutions for GDCNs of various scales. For small-scale GDCNs, we propose an analytical approach based on convex programming. For medium-scale GDCNs, we develop a distributed allocation algorithm exploiting the processing power of DCs in parallel. Afterward, we provide a novel low-complexity (decentralized) sub-graph extraction method, based on which we introduce cloud crawlers aiming to extract allocations of good potentials for large-scale GDCNs. Given these suggested strategies, we further investigate strategy selection under both fixed and adaptive DC pricing schemes, and propose an online learning algorithm for each.
