Research

Spectrum Sharing Networks - In wireless communication networks, the network provider serves certain licensed primary users who pay for a dedicated use of the frequency channels. However, not all the channels are occupied by the primary users at all times. For efficient spectrum utilization, in centralized cognitive radio networks (CRNs), a cognitive base station (CBS) dynamically identifies the spectrum holes and allocates the frequency channels to the on-demand unlicensed secondary users known as cognitive radios (CRs). Although existing literature has developed various dynamic spectrum access mechanisms for CBS, there is still a dearth of studies due to the wide range of assumptions made in the solutions. Most of the existing works study the CBS scheduling problem scheme by adopting optimization-based methods and rely on the prior knowledge of the network parameters such as primary users’ activity. Moreover, the impact of channel switching costs on the network throughput has not been well studied. In this paper, we aim to maximize the CRNs total throughput, and we formulate the CBS scheduling problem as a non-stochastic (i.e., adversarial) combinatorial multi-armed bandit problem with semi-bandit feedback and arm switching costs. We propose two novel online learning algorithms for CBS scheduling with and without channel switching costs, where their regret performances are proved sublinear order-optimal in time as T1/2 and T2/3, respectively, offering throughput-optimal scheduling for CRNs. Experiments on the synthetic and real-world spectrum measurement data complement and validate our theoretical findings.

"Multiuser Scheduling in Centralized Cognitive Radio Networks: A Multi-Armed Bandit Approach"

A. Alipour-Fanid, M. Dabaghchian, R. Arora, K. Zeng

IEEE Transactions on Cognitive Communications and Networking (TCCN)

UAV Detection - The consumer unmanned aerial vehicle (UAV) market has grown significantly over the past few years. Despite its huge potential in spurring economic growth by supporting various applications, the increase of consumer UAVs poses potential risks to public security and personal privacy. To minimize the risks, efficiently detecting and identifying invading UAVs is in urgent need for both invasion detection and forensics purposes. Aiming to complement the existing physical detection mechanisms, we propose a machine learning-based framework for fast UAV identification over encrypted Wi-Fi traffic.

"Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification over Encrypted Wi-Fi Traffic"

A. Alipour-Fanid, M. Dabaghchian, N. Wang, P. Wang, L. Zhao, K. Zeng

IEEE Transactions on Information Forensics & Security (TIFS)

Vehicular Cyber-Physical System Security - Cooperative Adaptive Cruise Control (CACC) is considered as a key enabling technology to automatically regulate the inter-vehicle distances in a vehicle string, and improve the traffic throughput efficiency. In the existing CACC systems, the coupling between wireless communication uncertainty, and system states is not well modeled. In this paper, we integrate the jamming attacks, and wireless channel fading effects into the CACC state space equations such that it effectively captures the coupling impact. Then, we propose a novel time domain approach to analyze the mean string stability (MSS) of such a model. Based on the proposed model, we analyze the impact of the jammer's location on the string stability.

"Impact of Jamming Attacks on Vehicular Cooperative Adaptive Cruise Control Systems"

A. Alipour-Fanid, M. Dabaghchian, K. Zeng

IEEE Transactions on Vehicular Technology (TVT)

Wireless CPS Security- We study security of remote state estimation in wireless cyber-physical systems (CPS) where a sensor sends its measurements to the remote state estimator over a multi-channel wireless link in presence of a jamming attacker. Most of the existing works study the sensor’s defense scheme by adopting optimization-based methods and rely on the prior knowledge of the attacker’s attack policy. To relax this constraint, we propose a novel online learning-based policy called J-CAP (Joint Channel And Power selection) for the sensor to dynamically choose transmission channel and power. The proposed method assumes no prior knowledge of the attacker’s attack policy, nor of the channel state information. J-CAP jointly optimizes sensor’s channel selection and power consumption, and guarantees the estimator’s asymptotic stability. We theoretically prove that JCAP achieves a sublinear learning regret bound. We also show J-CAP’s optimality by deriving and matching its regret lower and upper bound orders

"Online Learning-Based Defense Against Jamming Attacks in Multi-Channel Wireless CPS"

A. Alipour-Fanid, M. Dabaghchian, N. Wang, L. Jiao, K. Zeng

IEEE Internet of Things Journal (IoT-J)

Cognitive Radio Networks Security - In a cognitive radio network, a secondary user learns the spectrum environment and dynamically accesses the channel, where the primary user is inactive. At the same time, a primary user emulation (PUE) attacker can send falsified primary user signals and prevent the secondary user from utilizing the available channel. The best attacking strategies that an attacker can apply have not been well studied. In this paper, for the first time, we study optimal PUE attack strategies by formulating an online learning problem, where the attacker needs to dynamically decide the attacking channel in each time slot based on its attacking experience. The challenge in our problem is that since the PUE attack happens in the spectrum sensing phase, the attacker cannot observe the reward on the attacked channel. To address this challenge, we utilize the attacker's observation capability. We propose online learning-based attacking strategies based on the attacker's observation capabilities.

"Online Learning with Randomized Feedback Graphs for Optimal PUE Attacks in Cognitive Radio Networks"

M. Dabaghchian, A. Alipour-Fanid, K. Zeng, Q. Wang, P. Auer

IEEE/ACM Transactions on Networking (ToN)

Multi-Armed Bandits Problems - We study a family of multi-armed bandit (MAB) problems, wherein, not only the player cannot observe the reward on the played arm (self-unaware player), but also it incurs switching costs when shifting to a new arm. We study two cases: In Case 1, at each round, the player is able to either play or observe the chosen arm but not both. In Case 2, the player can choose an arm to play, and at the same round, choose another arm to observe. In both cases, the player incurs a cost for consecutive arm switching due to playing or observing the arms. We propose two novel online learning-based algorithms each addressing one of the aforementioned MAB problems. We theoretically prove that the proposed algorithms for Case 1 and Case 2, achieve sublinear order-optimal regret.

"Self-Unaware Adversarial Multi-Armed Bandits with Switching Costs"

A. Alipour-Fanid, M. Dabaghchian, K. Zeng

IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Efficient Classification - As machine learning methods are utilized in more and more real-world applications involving constraints on computational budgets, the systematic integration of such constraints into the process of model selection and model optimization is required to an increasing extent. A specific computational resource in this regard is the time needed for evaluating predictions on test instances. There is meanwhile a substantial body of work concerned with the joint optimization of accuracy and test-time efficiency by considering the time costs of feature generation and model prediction. During the feature generation process, significant redundant computations across different features occur in many applications.

"Prediction-time Efficient Classification Using Feature Computational Dependencies"

L. Zhao, A. Alipour-Fanid, M. Slawski, K. Zeng

Knowledge Discovery and Data Mining (KDD)

5G mm-Wave Massive MIMO Networks Security - Power non-orthogonal multiple access (NOMA) has been considered as a new enabling technology in 5G communication. In this paper, we introduce the problem of pilot contamination attack (PCA) on NOMA in millimeter wave (mmWave) and massive MIMO 5G communication. Due to the new characteristics of NOMA such as superposed signals with multiusers, PCA detection faces new challenges. By harnessing the sparseness and statistics of mmWave and massive MIMO virtual channel, we propose two effective PCA detection schemes for NOMA tackling static and dynamic environments, respectively. For the static environment, the problem of PCA detection is formulated as a binary hypothesis test of the virtual channel sparsity. For the dynamic environment, the statistic of the peaks in the virtual channel is leveraged to distinguish the contamination state from the normal state. A peak estimation algorithm and a machine learning based detection framework are proposed to achieve high detection performance.

Pilot Contamination Attack Detection for NOMA in 5G mm-Wave Massive MIMO Networks

N. Wang , L. Jiao, A. Alipour-Fanid, M. Dabaghchian, K. Zeng

IEEE Transactions on Information Forensics & Security (TIFS)