arXiv subjects

Kemal Davaslioglu

Publications and source records attributed to Kemal Davaslioglu.

At least 37 records · Page 2Linked to original sources

arXiv2020

Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers

This paper presents how to leak private information from a wireless signal classifier by launching an over-the-air membership inference attack (MIA). As machine learning (ML) algorithms are used to process wireless signals to make decisions such as PHY-layer authentication, the training data characteristics (e.g., device-level information) and the environment conditions (e.g., channel information) under which the data is collected may leak to the ML model. As a privacy threat, the adversary can use this leaked information to exploit vulnerabilities of the ML model following an adversarial ML approach. In this paper, the MIA is launched against a deep learning-based classifier that uses waveform, device, and channel characteristics (power and phase shifts) in the received signals for RF fingerprinting. By observing the spectrum, the adversary builds first a surrogate classifier and then an inference model to determine whether a signal of interest has been used in the training data of the receiver (e.g., a service provider). The signal of interest can then be associated with particular device and channel characteristics to launch subsequent attacks. The probability of attack success is high (more than 88% depending on waveform and channel conditions) in identifying signals of interest (and potentially the device and channel information) used to build a target classifier. These results show that wireless signal classifiers are vulnerable to privacy threats due to the over-the-air information leakage of their ML models

eess.SP↗

arXiv2020

How to Make 5G Communications "Invisible": Adversarial Machine Learning for Wireless Privacy

We consider the problem of hiding wireless communications from an eavesdropper that employs a deep learning (DL) classifier to detect whether any transmission of interest is present or not. There exists one transmitter that transmits to its receiver in the presence of an eavesdropper, while a cooperative jammer (CJ) transmits carefully crafted adversarial perturbations over the air to fool the eavesdropper into classifying the received superposition of signals as noise. The CJ puts an upper bound on the strength of perturbation signal to limit its impact on the bit error rate (BER) at the receiver. We show that this adversarial perturbation causes the eavesdropper to misclassify the received signals as noise with high probability while increasing the BER only slightly. On the other hand, the CJ cannot fool the eavesdropper by simply transmitting Gaussian noise as in conventional jamming and instead needs to craft perturbation signals built by adversarial machine learning to enable covert communications. Our results show that signals with different modulation types and eventually 5G communications can be effectively hidden from an eavesdropper even if it is equipped with a DL classifier to detect transmissions.

eess.SP↗

arXiv2020

Over-the-Air Adversarial Attacks on Deep Learning Based Modulation Classifier over Wireless Channels

We consider a wireless communication system that consists of a transmitter, a receiver, and an adversary. The transmitter transmits signals with different modulation types, while the receiver classifies its received signals to modulation types using a deep learning-based classifier. In the meantime, the adversary makes over-the-air transmissions that are received as superimposed with the transmitter's signals to fool the classifier at the receiver into making errors. While this evasion attack has received growing interest recently, the channel effects from the adversary to the receiver have been ignored so far such that the previous attack mechanisms cannot be applied under realistic channel effects. In this paper, we present how to launch a realistic evasion attack by considering channels from the adversary to the receiver. Our results show that modulation classification is vulnerable to an adversarial attack over a wireless channel that is modeled as Rayleigh fading with path loss and shadowing. We present various adversarial attacks with respect to availability of information about channel, transmitter input, and classifier architecture. First, we present two types of adversarial attacks, namely a targeted attack (with minimum power) and non-targeted attack that aims to change the classification to a target label or to any other label other than the true label, respectively. Both are white-box attacks that are transmitter input-specific and use channel information. Then we introduce an algorithm to generate adversarial attacks using limited channel information where the adversary only knows the channel distribution. Finally, we present a black-box universal adversarial perturbation (UAP) attack where the adversary has limited knowledge about both channel and transmitter input.

eess.SP↗

arXiv2019

DeepWiFi: Cognitive WiFi with Deep Learning

We present the DeepWiFi protocol, which hardens the baseline WiFi (IEEE 802.11ac) with deep learning and sustains high throughput by mitigating out-of-network interference. DeepWiFi is interoperable with baseline WiFi and builds upon the existing WiFi's PHY transceiver chain without changing the MAC frame format. Users run DeepWiFi for i) RF front end processing; ii) spectrum sensing and signal classification; iii) signal authentication; iv) channel selection and access; v) power control; vi) modulation and coding scheme (MCS) adaptation; and vii) routing. DeepWiFi mitigates the effects of probabilistic, sensing-based, and adaptive jammers. RF front end processing applies a deep learning-based autoencoder to extract spectrum-representative features. Then a deep neural network is trained to classify waveforms reliably as idle, WiFi, or jammer. Utilizing channel labels, users effectively access idle or jammed channels, while avoiding interference with legitimate WiFi transmissions (authenticated by machine learning-based RF fingerprinting) resulting in higher throughput. Users optimize their transmit power for low probability of intercept/detection and their MCS to maximize link rates used by backpressure algorithm for routing. Supported by embedded platform implementation, DeepWiFi provides major throughput gains compared to baseline WiFi and another jamming-resistant protocol, especially when channels are likely to be jammed and the signal-to-interference-plus-noise-ratio is low.

cs.NI↗

arXiv2019

Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning

We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation types as labels. An adversary slightly manipulates training data by inserting Trojans (i.e., triggers) to only few training data samples by modifying their phases and changing the labels of these samples to a target label. This poisoned training data is used to train the deep learning classifier. In test (inference) time, an adversary transmits signals with the same phase shift that was added as a trigger during training. While the receiver can accurately classify clean (unpoisoned) signals without triggers, it cannot reliably classify signals poisoned with triggers. This stealth attack remains hidden until activated by poisoned inputs (Trojans) to bypass a signal classifier (e.g., for authentication). We show that this attack is successful over different channel conditions and cannot be mitigated by simply preprocessing the training and test data with random phase variations. To detect this attack, activation based outlier detection is considered with statistical as well as clustering techniques. We show that the latter one can detect Trojan attacks even if few samples are poisoned.

cs.NI↗

arXiv2019

Real-Time and Embedded Deep Learning on FPGA for RF Signal Classification

We designed and implemented a deep learning based RF signal classifier on the Field Programmable Gate Array (FPGA) of an embedded software-defined radio platform, DeepRadio, that classifies the signals received through the RF front end to different modulation types in real time and with low power. This classifier implementation successfully captures complex characteristics of wireless signals to serve critical applications in wireless security and communications systems such as identifying spoofing signals in signal authentication systems, detecting target emitters and jammers in electronic warfare (EW) applications, discriminating primary and secondary users in cognitive radio networks, interference hunting, and adaptive modulation. Empowered by low-power and low-latency embedded computing, the deep neural network runs directly on the FPGA fabric of DeepRadio, while maintaining classifier accuracy close to the software performance. We evaluated the performance when another SDR (USRP) transmits signals with different modulation types at different power levels and DeepRadio receives the signals and classifies them in real time on its FPGA. A smartphone with a mobile app is connected to DeepRadio to initiate the experiment and visualize the classification results. With real radio transmissions over the air, we show that the classifier implemented on DeepRadio achieves high accuracy with low latency (microsecond per sample) and low energy consumption (microJoule per sample), and this performance is not matched by other embedded platforms such as embedded graphics processing unit (GPU).

cs.NI↗

arXiv2019

QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning

The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks. To ensure robust communication against jamming, an interference-aware routing protocol is developed that allows nodes to avoid communication holes created by jamming attacks. Then, a distributed cooperation framework, based on deep reinforcement learning, is proposed that allows nodes to assess network conditions and make deep learning-driven, distributed, and real-time decisions on whether to participate in data communications, defend the network against jamming and eavesdropping attacks, or jam other transmissions. The objective is to maximize the network performance that incorporates throughput, energy efficiency, delay, and security metrics. Simulation results show that the proposed jamming-aware routing approach is robust against jamming and when throughput is prioritized, the proposed deep reinforcement learning approach can achieve significant (measured as three-fold) increase in throughput, compared to a benchmark policy with fixed roles assigned to nodes.

cs.NI↗

arXiv2019

Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments

Dynamic spectrum access (DSA) benefits from detection and classification of interference sources including in-network users, out-network users, and jammers that may all coexist in a wireless network. We present a deep learning based signal (modulation) classification solution in a realistic wireless network setting, where 1) signal types may change over time; 2) some signal types may be unknown for which there is no training data; 3) signals may be spoofed such as the smart jammers replaying other signal types; and 4) different signal types may be superimposed due to the interference from concurrent transmissions. For case 1, we apply continual learning and train a Convolutional Neural Network (CNN) using an Elastic Weight Consolidation (EWC) based loss. For case 2, we detect unknown signals via outlier detection applied to the outputs of convolutional layers using Minimum Covariance Determinant (MCD) and k-means clustering methods. For case 3, we extend the CNN structure to capture phase shifts due to radio hardware effects to identify the spoofing signal sources. For case 4, we apply blind source separation using Independent Component Analysis (ICA) to separate interfering signals. We utilize the signal classification results in a distributed scheduling protocol, where in-network (secondary) users employ signal classification scores to make channel access decisions and share the spectrum with each other while avoiding interference with out-network (primary) users and jammers. Compared with benchmark TDMA-based schemes, we show that distributed scheduling constructed upon signal classification results provides major improvements to in-network user throughput and out-network user success ratio.

cs.NI↗

arXiv2019

Generative Adversarial Network for Wireless Signal Spoofing

The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount importance to authenticate wireless signals at the PHY layer before they proceed through the receiver chain. For that purpose, various waveform, channel, and radio hardware features that are inherent to original wireless signals need to be captured. In the meantime, adversaries become sophisticated with the cognitive radio capability to record, analyze, and manipulate signals before spoofing. Building upon deep learning techniques, this paper introduces a spoofing attack by an adversary pair of a transmitter and a receiver that assume the generator and discriminator roles in the GAN and play a minimax game to generate the best spoofing signals that aim to fool the best trained defense mechanism. The output of this approach is two-fold. From the attacker point of view, a deep learning-based spoofing mechanism is trained to potentially fool a defense mechanism such as RF fingerprinting. From the defender point of view, a deep learning-based defense mechanism is trained against potential spoofing attacks when an adversary pair of a transmitter and a receiver cooperates. The probability that the spoofing signal is misclassified as the intended signal is measured for random signal, replay, and GAN-based spoofing attacks. Results show that the GAN-based spoofing attack provides a major increase in the success probability of wireless signal spoofing even when a deep learning classifier is used as the defense.

eess.SP↗

arXiv2019

Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data

As online systems based on machine learning are offered to public or paid subscribers via application programming interfaces (APIs), they become vulnerable to frequent exploits and attacks. This paper studies adversarial machine learning in the practical case when there are rate limitations on API calls. The adversary launches an exploratory (inference) attack by querying the API of an online machine learning system (in particular, a classifier) with input data samples, collecting returned labels to build up the training data, and training an adversarial classifier that is functionally equivalent and statistically close to the target classifier. The exploratory attack with limited training data is shown to fail to reliably infer the target classifier of a real text classifier API that is available online to the public. In return, a generative adversarial network (GAN) based on deep learning is built to generate synthetic training data from a limited number of real training data samples, thereby extending the training data and improving the performance of the inferred classifier. The exploratory attack provides the basis to launch the causative attack (that aims to poison the training process) and evasion attack (that aims to fool the classifier into making wrong decisions) by selecting training and test data samples, respectively, based on the confidence scores obtained from the inferred classifier. These stealth attacks with small footprint (using a small number of API calls) make adversarial machine learning practical under the realistic case with limited training data available to the adversary.

cs.LG↗

arXiv2018

Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls

Machine learning has been applied to a broad range of applications and some of them are available online as application programming interfaces (APIs) with either free (trial) or paid subscriptions. In this paper, we study adversarial machine learning in the form of back-box attacks on online classifier APIs. We start with a deep learning based exploratory (inference) attack, which aims to build a classifier that can provide similar classification results (labels) as the target classifier. To minimize the difference between the labels returned by the inferred classifier and the target classifier, we show that the deep learning based exploratory attack requires a large number of labeled training data samples. These labels can be collected by calling the online API, but usually there is some strict rate limitation on the number of allowed API calls. To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels. Then, a new classifier is built using more training data samples. This updating process can be repeated multiple times. We show that this active learning approach can build an adversarial classifier with a small statistical difference from the target classifier using only a limited number of training data samples. We further consider evasion and causative (poisoning) attacks based on the inferred classifier that is built by the exploratory attack. Evasion attack determines samples that the target classifier is likely to misclassify, whereas causative attack provides erroneous training data samples to reduce the reliability of the re-trained classifier. The success of these attacks show that adversarial machine learning emerges as a feasible threat in the realistic case with limited training data.

cs.LG↗

arXiv2018

Generative Adversarial Learning for Spectrum Sensing

A novel approach of training data augmentation and domain adaptation is presented to support machine learning applications for cognitive radio. Machine learning provides effective tools to automate cognitive radio functionalities by reliably extracting and learning intrinsic spectrum dynamics. However, there are two important challenges to overcome, in order to fully utilize the machine learning benefits with cognitive radios. First, machine learning requires significant amount of truthed data to capture complex channel and emitter characteristics, and train the underlying algorithm (e.g., a classifier). Second, the training data that has been identified for one spectrum environment cannot be used for another one (e.g., after channel and emitter conditions change). To address these challenges, a generative adversarial network (GAN) with deep learning structures is used to 1)~generate additional synthetic training data to improve classifier accuracy, and 2) adapt training data to spectrum dynamics. This approach is applied to spectrum sensing by assuming only limited training data without knowledge of spectrum statistics. Machine learning classifiers are trained with limited, augmented and adapted training data to detect signals. Results show that training data augmentation increases the classifier accuracy significantly and this increase is sustained with domain adaptation as spectrum conditions change.

cs.NI↗

arXiv2016

New Algorithms for Maximizing Cellular Wireless Network Energy Efficiency

In this paper, we aim to maximize the energy efficiency of cellular wireless networks. Specifically, we address the power allocation problem in multi-cell multi-carrier systems. Considering realistic base station power consumption models, we formulate a network-wide energy efficiency maximization problem. Using tools from fractional programming, we cast this problem in the framework of bi-criterion optimization where rate maximization and power minimization are weighted accordingly. Interference pricing mechanism is applied to reduce the intercell interference and to achieve a higher network performance. We decompose the main problem into subproblems via dual decomposition. These subproblems are independently solved per sector using limited information exchange between base stations. We first derive our expressions and present algorithms for the single-tier networks. Then, we extend our analysis to two-tier networks where picocell base stations are deployed to improve the network performance and reduce the link distances. Lastly, we extend our framework and include the quality-of-service constraints.We obtain closed-form expressions for the power level updates which are determined by the multi-level water-filling algorithm, or, as it is sometimes called as, the modified waterfilling algorithm. Based on our simulation results, we demonstrate that the proposed algorithms can outperform the benchmark approaches in terms of energy efficiency by a factor of 2.7.

cs.NI↗

arXiv2016

Energy Efficiency Optimization of Channel Access Probabilities in IEEE 802.15.6 UWB WBANs

Energy efficiency is essential for Wireless Body Area Network (WBAN) applications because of the battery-operated nodes. Other requirements such as throughput, delay, quality of service, and security levels also need to be considered in optimizing the network design. In this paper, we study the case in which the nodes access the medium probabilistically and we formulate an energy efficiency optimization problem under the rate and access probability constraints for IEEE 802.15.6 Impulse Radio Ultra-wideband (IR-UWB) WBANs. The proposed algorithm, dubbed Energy Efficiency Optimization of Channel Access Probabilities (EECAP), determines the optimal access probability and payload frame size for each node. The simulation results show that our algorithm rapidly converges to the optimal solution. We also provide detailed insights on the relationship between the optimal access probabilities and other network parameters such as the link distance, the number of nodes, and the minimum rate constraints.

cs.NI↗

arXiv2016

CLOEE - Cross-Layer Optimization for Energy Efficiency of IEEE 802.15.6 IR-UWB WBANs

Advances in sensor networks enable pervasive health monitoring and patient-specific treatments that take into account the patients medical history, current state, genetic background, and personal habits. However, sensors are often battery power limited and vastly differ in their application related requirements. In this paper, we address both of these problems. Specifically, we study IEEE 802.15.6 ultra-wideband (UWB) wireless body area networks (WBANs) that use impulse radio (IR). We formulate the joint optimization of the payload size and number of pulses per symbol to optimize the energy efficiency under the minimum rate constraint. The proposed algorithm, cross-layer optimization for energy efficiency (CLOEE), enables us to carry out a cross-layer resource allocation that addresses the rate and reliability trade-off in the physical (PHY) layer as well as the packet size optimization and transmission efficiency for the medium access control (MAC) layer. Simulation results demonstrate that CLOEE can provide an order of magnitude improvement in to static strategies.

cs.NI↗

arXiv2015

Quantifying Potential Energy Efficiency Gain in Green Cellular Wireless Networks

Conventional cellular wireless networks were designed with the purpose of providing high throughput for the user and high capacity for the service provider, without any provisions of energy efficiency. As a result, these networks have an enormous Carbon footprint. In this paper, we describe the sources of the inefficiencies in such networks. First we present results of the studies on how much Carbon footprint such networks generate. We also discuss how much more mobile traffic is expected to increase so that this Carbon footprint will even increase tremendously more. We then discuss specific sources of inefficiency and potential sources of improvement at the physical layer as well as at higher layers of the communication protocol hierarchy. In particular, considering that most of the energy inefficiency in cellular wireless networks is at the base stations, we discuss multi-tier networks and point to the potential of exploiting mobility patterns in order to use base station energy judiciously. We then investigate potential methods to reduce this inefficiency and quantify their individual contributions. By a consideration of the combination of all potential gains, we conclude that an improvement in energy consumption in cellular wireless networks by two orders of magnitude, or even more, is possible.

cs.NI↗

arXiv2014

Energy-Efficient Resource Allocation for Fractional Frequency Reuse in Heterogeneous Networks

Next generation wireless networks face the challenge of increasing energy consumption while satisfying the unprecedented increase in the data rate demand. To address this problem, we propose a utility-based energy-efficient resource allocation algorithm for the downlink transmissions in heterogeneous networks (HetNets). We consider the fractional frequency reuse (FFR) method in order to mitigate the intra- and inter-cell interference. The proposed algorithm divides the resource allocation problem into frequency and power assignment problems and sequentially solves them. The proposed power control algorithm uses the gradient ascent method to control the transmit power of macrocell base stations as most of the power in the network is consumed there. We also present the optimality conditions of the resource allocation problem and the convergence of the proposed algorithm. We study the performance of the proposed algorithm in a Long Term Evolution (LTE) system. Our simulation results demonstrate that the proposed algorithm provides substantial improvements in the energy efficiency and throughput of the network.

cs.NI↗

arXiv2013

Impulse Radio Ultra-Wideband Communication Over Free-Space Optical Links

A composite impulse radio ultra-wideband (IR-UWB) communication system is presented. The proposed system model aims to transmit UWB pulses over several kilometers through free-space optical (FSO) links and depending on the link design, the electrical estimates of the FSO system can be directly used or distributed to end-user through radio-frequency (RF) links over short ranges. However, inhomogeneities on the FSO transmission path cause random fluctuations in the received signal intensity and these effects induced by atmospheric turbulence closely effect the system performance. Several distinct probability distributions based on experimental measurements are used to characterize FSO channels and using these probabilistic models, detection error probability analysis of the proposed system for different link designs are carried out under weak, moderate and strong turbulence conditions. The results of the analysis show that depending on the atmospheric conditions, system performance of the composite link can have high error floors due to the false estimates of FSO link. The system performance can be improved by employing error control coding techniques. One simple solution employing a convolutional encoder and Viterbi decoder pair is also analyzed in this thesis. Another important system parameter that is the average channel capacity of the FSO system is analyzed under weak and moderate turbulence conditions. Theoretical derivations that are verified via simulation results indicate a reliable high data rate communication system that is effective in long distances.

physics.optics↗