Search

The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating the susceptibility of DL-based classification tasks to adversarial attacks, regression-based problems in the context of a wireless system have not been studied so far from an attack perspective. The aim of this paper is twofold: (i) we consider a regression problem in a wireless setting and show that adversarial attacks can break the DL-based approach and (ii) we analyze the effectiveness of adversarial training as a defensive technique in adversarial settings and show that the robustness of DL-based wireless system against attacks improves significantly. Specifically, the wireless application considered in this paper is the DL-based power allocation in the downlink of a multicell massive multi-input-multi-output system, where the goal of the attack is to yield an infeasible solution by the DL model. We extend the gradient-based adversarial attacks: fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent method to analyze the susceptibility of the considered wireless application with and without adversarial training. We analyze the deep neural network (DNN) models performance against these attacks, where the adversarial perturbations are crafted using both the white-box and black-box attacks., Comment: 13 pages, 14 figures, published in IEEE Transactions on Cognitive Communications and Networking

We study joint unicast and multigroup multicast transmission in single-cell massive multiple-input-multiple-output (MIMO) systems, under maximum ratio transmission. For the unicast transmission, the objective is to maximize the weighted sum spectral efficiency (SE) of the unicast user terminals (UTs) and for the multicast transmission the objective is to maximize the minimum SE of the multicast UTs. These two problems are coupled to each other in a conflicting manner, due to their shared power resource and interference. To address this, we formulate a multiobjective optimization problem (MOOP). We derive the Pareto boundary of the MOOP analytically and determine the values of the system parameters to achieve any desired Pareto optimal point. Moreover, we prove that the Pareto region is convex, hence the system should serve the unicast and multicast UTs at the same time-frequency resource., Comment: Published at 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 5 pages, 1 figure. arXiv admin note: substantial text overlap with arXiv:1911.08165

Deep learning (DL) architectures have been successfully used in many applications including wireless systems. However, they have been shown to be susceptible to adversarial attacks. We analyze DL-based models for a regression problem in the context of downlink power allocation in massive multiple-input-multiple-output systems and propose universal adversarial perturbation (UAP)-crafting methods as white-box and black-box attacks. We benchmark the UAP performance of white-box and black-box attacks for the considered application and show that the adversarial success rate can achieve up to 60% and 40%, respectively. The proposed UAP-based attacks make a more practical and realistic approach as compared to classical white-box attacks., Comment: accepted for publication in IEEE Wireless Communications Letters

Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are susceptible to adversarial examples; adversarial examples are well-crafted malicious inputs to the neural network (NN) with the objective to cause erroneous outputs. In this paper, we extend this to regression problems and show that adversarial attacks can break DL-based power allocation in the downlink of a massive multiple-input-multiple-output (maMIMO) network. Specifically, we extend the fast gradient sign method (FGSM), momentum iterative FGSM, and projected gradient descent adversarial attacks in the context of power allocation in a maMIMO system. We benchmark the performance of these attacks and show that with a small perturbation in the input of the NN, the white-box attacks can result in infeasible solutions up to 86%. Furthermore, we investigate the performance of black-box attacks. All the evaluations conducted in this work are based on an open dataset and NN models, which are publicly available., Comment: to be published in proceedings of IEEE International Conference on Communications (ICC) 2021

We study the joint unicast and multi-group multicast transmission in massive multiple-input-multiple-output (MIMO) systems. We consider a system model that accounts for channel estimation and pilot contamination, and derive achievable spectral efficiencies (SEs) for unicast and multicast user terminals (UTs), under maximum ratio transmission and zero-forcing precoding. For unicast transmission, our objective is to maximize the weighted sum SE of the unicast UTs, and for the multicast transmission, our objective is to maximize the minimum SE of the multicast UTs. These two objectives are coupled in a conflicting manner, due to their shared power resource. Therefore, we formulate a multiobjective optimization problem (MOOP) for the two conflicting objectives. We derive the Pareto boundary of the MOOP analytically. As each Pareto optimal point describes a particular efficient trade-off between the two objectives of the system, we determine the values of the system parameters (uplink training powers, downlink transmission powers, etc.) to achieve any desired Pareto optimal point. Moreover, we prove that the Pareto region is convex, hence the system should serve the unicast and multicast UTs at the same time-frequency resource. Finally, we validate our results using numerical simulations., Comment: Published in IEEE Transactions on Wireless Communications, 29 pages, 5 figures

We show that end-to-end learning of communication systems through deep neural network (DNN) autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft effective physical black-box adversarial attacks. Due to the openness (broadcast nature) of the wireless channel, an adversary transmitter can increase the block-error-rate of a communication system by orders of magnitude by transmitting a well-designed perturbation signal over the channel. We reveal that the adversarial attacks are more destructive than jamming attacks. We also show that classical coding schemes are more robust than autoencoders against both adversarial and jamming attacks. The codes are available at [1]., Comment: to appear at IEEE Communications Letters

Deep learning (DL), despite its enormous success in many computer vision and language processing applications, is exceedingly vulnerable to adversarial attacks. We consider the use of DL for radio signal (modulation) classification tasks, and present practical methods for the crafting of white-box and universal black-box adversarial attacks in that application. We show that these attacks can considerably reduce the classification performance, with extremely small perturbations of the input. In particular, these attacks are significantly more powerful than classical jamming attacks, which raises significant security and robustness concerns in the use of DL-based algorithms for the wireless physical layer., Comment: 4 pages

Optimal physical layer multicasting (PLM) is an NP-hard problem that for simplicity has been studied under idealistic assumptions, e.g., availability of perfect channel state information (CSI), both at the base station (BS) and at the user terminals (UTs). With the advent of massive multiple-input-multiple-output (MIMO), PLM has become more challenging, as the computational complexity of the precoder design is proportional to the number of BS antennas. In this paper, we address these issues by introducing computationally efficient precoders that account for practical CSI acquisition. We derive achievable spectral efficiency expressions for the proposed precoders. Then we introduce a novel problem formulation for the max-min fairness power control that accounts the CSI acquisition overhead, uplink training and downlink transmission powers. We solve this problem and find the optimal uplink and downlink power control policies in closed form. Using numerical simulations, we verify the effectiveness of our proposed schemes compared to the-state-of-the-art PLM schemes for massive MIMO systems., Comment: to appear at IEEE GLOBECOM 2017

This paper considers the downlink precoding for physical layer multicasting in massive multiple-input-multiple-output (MIMO) systems. We study the max-min fairness (MMF) problem, where channel state information (CSI) at the transmitter is used to design precoding vectors that maximize the minimum spectral efficiency (SE) of the system, given fixed power budgets for uplink training and downlink transmission. Our system model accounts for channel estimation, pilot contamination, arbitrary pathlosses, and multi-group multicasting. We consider six scenarios with different transmission technologies (unicast and multicast), different pilot assignment strategies (dedicated or shared pilot assignments), and different precoding schemes (maximum ratio transmission and zero forcing), and derive achievable spectral efficiencies for all possible combinations. Then we solve the MMF problem for each of these scenarios and for any given pilot length we find the SE maximizing uplink pilot and downlink data transmission policies, all in closed-forms. We use these results to draw a general guideline for massive MIMO multicasting design, where for a given number of base station antennas, number of users, and coherence interval length, we determine the multicasting scheme that shall be used.

Linear precoding has been widely studied in the context of Massive multiple-input-multiple-output (MIMO) together with two common power normalization techniques, namely, matrix normalization (MN) and vector normalization (VN). Despite this, their effect on the performance of Massive MIMO systems has not been thoroughly studied yet. The aim of this paper is to fulfill this gap by using large system analysis. Considering a system model that accounts for channel estimation, pilot contamination, arbitrary pathloss, and per-user channel correlation, we compute tight approximations for the signal-to-interference-plus-noise ratio and the rate of each user equipment in the system while employing maximum ratio transmission (MRT), zero forcing (ZF), and regularized ZF precoding under both MN and VN techniques. Such approximations are used to analytically reveal how the choice of power normalization affects the performance of MRT and ZF under uncorrelated fading channels. It turns out that ZF with VN resembles a sum rate maximizer while it provides a notion of fairness under MN. Numerical results are used to validate the accuracy of the asymptotic analysis and to show that in Massive MIMO, non-coherent interference and noise, rather than pilot contamination, are often the major limiting factors of the considered precoding schemes., Comment: 12 pages, 3 figures, Accepted for publication in the IEEE Transactions on Vehicular Technology

Next generation of wireless networks will likely rely on large-scale antenna systems, either in the form of massive multi-input-multi-output (MIMO) or millimeter wave (mmWave) systems. Therefore, the conventional fully-digital precoders are not suitable for physical layer multicasting as they require a dedicated radio frequency chain per antenna element. In this paper, we show that in a multi-group multicasting system with an arbitrary number of transmit antennas, $G$ multicasting groups, and an arbitrary number of users in each group, one can achieve the performance of any fully-digital precoder with just $G$ radio frequency chains using the proposed hybrid multi-group multicasting structure., Comment: 5 pages, 5 figures, submitted to IEEE GLOBECOM 2017, Singapore, Dec. 2017

In this paper, we study the physical layer multicasting to multiple co-channel groups in large-scale antenna systems. The users within each group are interested in a common message and different groups have distinct messages. In particular, we aim at designing the precoding vectors solving the so-called quality of service (QoS) and weighted max-min fairness (MMF) problems, assuming that the channel state information is available at the base station (BS). To solve both problems, the baseline approach exploits the semidefinite relaxation (SDR) technique. Considering a BS with $N$ antennas, the SDR complexity is more than $\mathcal{O}(N^{6})$, which prevents its application in large-scale antenna systems. To overcome this issue, we present two new classes of algorithms that, not only have significantly lower computational complexity than existing solutions, but also largely outperform the SDR based methods. Moreover, we present a novel duality between transformed versions of the QoS and the weighted MMF problems. The duality explicitly determines the solution to the weighted MMF problem given the solution to the QoS problem, and vice versa. Numerical results are used to validate the effectiveness of the proposed solutions and to make comparisons with existing alternatives under different operating conditions., Comment: 13 pages, 7 figures, 2 tables