arXiv subjects

Aly El Gamal

Publications and source records attributed to Aly El Gamal.

At least 37 records · Page 2Linked to original sources

arXiv2020

Data-driven Analysis of Turbulent Flame Images

Turbulent premixed flames are important for power generation using gas turbines. Improvements in characterization and understanding of turbulent flames continue particularly for transient events like ignition and extinction. Pockets or islands of unburned material are features of turbulent flames during these events. These features are directly linked to heat release rates and hydrocarbons emissions. Unburned material pockets in turbulent CH$_4$/air premixed flames with CO$_2$ addition were investigated using OH Planar Laser-Induced Fluorescence images. Convolutional Neural Networks (CNN) were used to classify images containing unburned pockets for three turbulent flames with 0%, 5%, and 10% CO$_2$ addition. The CNN model was constructed using three convolutional layers and two fully connected layers using dropout and weight decay. The CNN model achieved accuracies of 91.72%, 89.35% and 85.80% for the three flames, respectively.

cs.CV↗

arXiv2020

Ensemble Wrapper Subsampling for Deep Modulation Classification

Subsampling of received wireless signals is important for relaxing hardware requirements as well as the computational cost of signal processing algorithms that rely on the output samples. We propose a subsampling technique to facilitate the use of deep learning for automatic modulation classification in wireless communication systems. Unlike traditional approaches that rely on pre-designed strategies that are solely based on expert knowledge, the proposed data-driven subsampling strategy employs deep neural network architectures to simulate the effect of removing candidate combinations of samples from each training input vector, in a manner inspired by how wrapper feature selection models work. The subsampled data is then processed by another deep learning classifier that recognizes each of the considered 10 modulation types. We show that the proposed subsampling strategy not only introduces drastic reduction in the classifier training time, but can also improve the classification accuracy to higher levels than those reached before for the considered dataset. An important feature herein is exploiting the transferability property of deep neural networks to avoid retraining the wrapper models and obtain superior performance through an ensemble of wrappers over that possible through solely relying on any of them.

eess.SP↗

arXiv2020

Grand Challenges in Resilience: Autonomous System Resilience through Design and Runtime Measures

A set of about 80 researchers, practitioners, and federal agency program managers participated in the NSF-sponsored Grand Challenges in Resilience Workshop held on Purdue campus on March 19-21, 2019. The workshop was divided into three themes: resilience in cyber, cyber-physical, and socio-technical systems. About 30 attendees in all participated in the discussions of cyber resilience. This article brings out the substantive parts of the challenges and solution approaches that were identified in the cyber resilience theme. In this article, we put forward the substantial challenges in cyber resilience in a few representative application domains and outline foundational solutions to address these challenges. These solutions fall into two broad themes: resilience-by-design and resilience-by-reaction. We use examples of autonomous systems as the application drivers motivating cyber resilience. We focus on some autonomous systems in the near horizon (autonomous ground and aerial vehicles) and also a little more distant (autonomous rescue and relief). For resilience-by-design, we focus on design methods in software that are needed for our cyber systems to be resilient. In contrast, for resilience-by-reaction, we discuss how to make systems resilient by responding, reconfiguring, or recovering at runtime when failures happen. We also discuss the notion of adaptive execution to improve resilience, execution transparently and adaptively among available execution platforms (mobile/embedded, edge, and cloud). For each of the two themes, we survey the current state, and the desired state and ways to get there. We conclude the paper by looking at the research challenges we will have to solve in the short and the mid-term to make the vision of resilient autonomous systems a reality.

cs.CR↗

arXiv2020

Efficient Training of Deep Classifiers for Wireless Source Identification using Test SNR Estimates

We study efficient deep learning training algorithms that process received wireless signals, if a test Signal to Noise Ratio (SNR) estimate is available. We focus on two tasks that facilitate source identification: 1- Identifying the modulation type, 2- Identifying the wireless technology and channel in the 2.4 GHz ISM band. For benchmarking, we rely on recent literature on testing deep learning algorithms against two well-known datasets. We first demonstrate that using training data corresponding only to the test SNR value leads to dramatic reductions in training time while incurring a small loss in average test accuracy, as it improves the accuracy for low SNR values. Further, we show that an erroneous test SNR estimate with a small positive offset is better for training than another having the same error magnitude with a negative offset. Secondly, we introduce a greedy training SNR Boosting algorithm that leads to uniform improvement in accuracy across all tested SNR values, while using a small subset of training SNR values at each test SNR. Finally, we demonstrate the potential of bootstrap aggregating (Bagging) based on training SNR values to improve generalization at low test SNR values with scarcity of training data.

cs.LG↗

arXiv2020

Towards Jointly Optimal Placement and Delivery: To Code or Not to Code in Wireless Caching Networks

Coded caching techniques have received significant attention lately due to their provable gains in reducing the cost of data delivery in wireless networks. These gains, however, have only been demonstrated under the assumption of a free placement phase. This unrealistic assumption poses a significant limitation, especially in cases where aggressive placement strategies can lead to a significant transmission cost that may even be higher than the corresponding cost of the delivery phase. In this paper, we relax this assumption and propose a general caching framework that captures the transmission cost of the two phases, and hence, results in minimizing the overall rate of the caching network. We model the dynamic nature of the network through a cost structure that allows for varying the network architecture and cost per transmission, across the placement and delivery phases. We start with the scenario where the individual users have no limit on the available caching memory and characterize the jointly optimal solution as a function of the different parameters in our cost structure. Then, we characterize the effect of memory constraints on the optimal solution in certain special cases. Interestingly, our results identify regions where the uncoded caching scheme outperforms its coded counterpart. Further, coded caching is shown to offer performance gains only when the network architecture during the placement phase is different from that during the delivery phase.

cs.IT↗

arXiv2020

Non-Intrusive Detection of Adversarial Deep Learning Attacks via Observer Networks

Recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this letter, we propose a novel method to detect adversarial inputs, by augmenting the main classification network with multiple binary detectors (observer networks) which take inputs from the hidden layers of the original network (convolutional kernel outputs) and classify the input as clean or adversarial. During inference, the detectors are treated as a part of an ensemble network and the input is deemed adversarial if at least half of the detectors classify it as so. The proposed method addresses the trade-off between accuracy of classification on clean and adversarial samples, as the original classification network is not modified during the detection process. The use of multiple observer networks makes attacking the detection mechanism non-trivial even when the attacker is aware of the victim classifier. We achieve a 99.5% detection accuracy on the MNIST dataset and 97.5% on the CIFAR-10 dataset using the Fast Gradient Sign Attack in a semi-white box setup. The number of false positive detections is a mere 0.12% in the worst case scenario.

cs.LG↗

arXiv2020

Ensemble Noise Simulation to Handle Uncertainty about Gradient-based Adversarial Attacks

Gradient-based adversarial attacks on neural networks can be crafted in a variety of ways by varying either how the attack algorithm relies on the gradient, the network architecture used for crafting the attack, or both. Most recent work has focused on defending classifiers in a case where there is no uncertainty about the attacker's behavior (i.e., the attacker is expected to generate a specific attack using a specific network architecture). However, if the attacker is not guaranteed to behave in a certain way, the literature lacks methods in devising a strategic defense. We fill this gap by simulating the attacker's noisy perturbation using a variety of attack algorithms based on gradients of various classifiers. We perform our analysis using a pre-processing Denoising Autoencoder (DAE) defense that is trained with the simulated noise. We demonstrate significant improvements in post-attack accuracy, using our proposed ensemble-trained defense, compared to a situation where no effort is made to handle uncertainty.

cs.LG↗

arXiv2020

Efficient Wrapper Feature Selection using Autoencoder and Model Based Elimination

We propose a computationally efficient wrapper feature selection method - called Autoencoder and Model Based Elimination of features using Relevance and Redundancy scores (AMBER) - that uses a single ranker model along with autoencoders to perform greedy backward elimination of features. The ranker model is used to prioritize the removal of features that are not critical to the classification task, while the autoencoders are used to prioritize the elimination of correlated features. We demonstrate the superior feature selection ability of AMBER on 4 well known datasets corresponding to different domain applications via comparing the classification accuracies with other computationally efficient state-of-the-art feature selection techniques. Interestingly, we find that the ranker model that is used for feature selection does not necessarily have to be the same as the final classifier that is trained on the selected features. Finally, we note how a smaller number of features can lead to higher accuracies on some datasets, and hypothesize that overfitting the ranker model on the training set facilitates the selection of more salient features.

cs.LG↗

arXiv2019

Optimal Wireless Caching with Placement Cost

Coded caching has been shown to result in significant throughput gains, but its gains were proved only by assuming a placement phase with no transmission cost. A free placement phase is, however, an unrealistic assumption that could stand as an obstacle towards delivering the promise of coded caching. In [1], we relaxed this assumption by introducing a general caching framework that captures transmission costs for both delivery and placement phases under general assumptions on varying network architectures, memory constraints, and traffic patterns. Here, we leverage this general framework and focus on analyzing the effect of the placement communication cost on the overall throughput and the structure of the optimal caching scheme, under the assumptions of the worst case traffic pattern and unlimited memory at the end users. Interestingly, we find relevant network configurations where uncoded caching is the optimal solution.

cs.IT↗

arXiv2019

Joint Uplink-Downlink Cooperative Interference Management with Flexible Cell Associations

We study information theoretic models of interference networks that consist of K Base Station (BS) - Mobile Terminal (MT) pairs. Each BS is connected to the MT carrying the same index as well as L following MTs. We fix the value of L and study the per user Degrees of Freedom (puDoF) in large networks. We assume that each MT can be associated with N BSs, and these associations are determined by a cloud-based controller that has a global view of the network. An MT has to be associated with a BS, for the BS to transmit its message in the downlink, or have its decoded message in the uplink. We propose puDoF inner bounds for arbitrary values of L when only the uplink is considered, and characterize the uplink puDoF value when only zero-forcing schemes are allowed. We then introduce new achievable average uplink-downlink puDoF values, and show their optimality for the range when N \leq (L/2) and when we restrict our attention to zero-forcing schemes. Additionally, for the remaining range, we characterize the optimal downlink scheme when the uplink-optimal associations are used. Finally, we show that the proposed scheme is information theoretically optimal for Wyner's linear interference network.

cs.IT↗

arXiv2019

A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks

The reliance on deep learning algorithms has grown significantly in recent years. Yet, these models are highly vulnerable to adversarial attacks, which introduce visually imperceptible perturbations into testing data to induce misclassifications. The literature has proposed several methods to combat such adversarial attacks, but each method either fails at high perturbation values, requires excessive computing power, or both. This letter proposes a computationally efficient method for defending the Fast Gradient Sign (FGS) adversarial attack by simultaneously denoising and compressing data. Specifically, our proposed defense relies on training a fully connected multi-layer Denoising Autoencoder (DAE) and using its encoder as a defense against the adversarial attack. Our results show that using this dimensionality reduction scheme is not only highly effective in mitigating the effect of the FGS attack in multiple threat models, but it also provides a 2.43x speedup in comparison to defense strategies providing similar robustness against the same attack.

cs.LG↗

arXiv2019

Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection

We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi. We employ deep learning algorithms trained on received samples taken from a 10 MHz band in the 2.4 GHz ISM Band. We obtain a classification accuracy of around 89.5% using any of four different deep neural network architectures: CNN, ResNet, CLDNN, and LSTM, which demonstrate the generality of the effectiveness of deep learning at the considered task. Interestingly, our proposed CNN architecture requires approximately 60% of the training time required by the state of the art while achieving slightly larger classification accuracy. We then focus on the CNN architecture and further optimize its training time while incurring minimal loss in classification accuracy using three different approaches: 1- Band Selection, where we only use samples belonging to the lower and uppermost 2 MHz bands, 2- SNR Selection, where we only use training samples belonging to a single SNR value, and 3- Sample Selection, where we try various sub-Nyquist sampling methods to select the subset of samples most relevant to the classification task. Our results confirm the feasibility of fast deep learning for wireless interference identification, by showing that the training time can be reduced by as much as 30x with minimal loss in accuracy.

eess.SP↗

arXiv2019

A Sampling Theory Perspective of Graph-based Semi-supervised Learning

Graph-based methods have been quite successful in solving unsupervised and semi-supervised learning problems, as they provide a means to capture the underlying geometry of the dataset. It is often desirable for the constructed graph to satisfy two properties: first, data points that are similar in the feature space should be strongly connected on the graph, and second, the class label information should vary smoothly with respect to the graph, where smoothness is measured using the spectral properties of the graph Laplacian matrix. Recent works have justified some of these smoothness conditions by showing that they are strongly linked to the semi-supervised smoothness assumption and its variants. In this work, we reinforce this connection by viewing the problem from a graph sampling theoretic perspective, where class indicator functions are treated as bandlimited graph signals (in the eigenvector basis of the graph Laplacian) and label prediction as a bandlimited reconstruction problem. Our approach involves analyzing the bandwidth of class indicator signals generated from statistical data models with separable and nonseparable classes. These models are quite general and mimic the nature of most real-world datasets. Our results show that in the asymptotic limit, the bandwidth of any class indicator is also closely related to the geometry of the dataset. This allows one to theoretically justify the assumption of bandlimitedness of class indicator signals, thereby providing a sampling theoretic interpretation of graph-based semi-supervised classification.

cs.LG↗

arXiv2019

Wyner's Network on Caches: Combining Receiver Caching with a Flexible Backhaul

In this work, we study a large linear interference network with an equal number of transmitters and receivers, where each transmitter is connected to two subsequent receivers. Each transmitter has individual access to a backhaul link (fetching the equivalent of $M_{T}$ files), while each receiver can cache a fraction $γ$ of the library. We explore the tradeoff between the communication rate, backhaul load, and caching storage by designing algorithms that can harness the benefits of cooperative transmission in partially connected networks, while exploiting the advantages of multicast transmissions attributed to user caching. We show that receiver caching and fetching content from the backhaul are two resources that can simultaneously increase the delivery performance in synergistic ways. Specifically, an interesting outcome of this work is that user caching of a fraction $γ$ of the library can increase the per-user Degrees of Freedom (puDoF) by $γ$. Further, the results reveal significant savings in the backhaul load, even in the small cache size region. For example, the puDoF achieved using the pair $(M_{T}=8, γ=0)$ can also be achieved with the pairs $(M_{T}=4,γ=0.035)$ and $(M_{T}=2,γ=0.1)$, showing that even small caches can provide significant savings in the backhaul load.

cs.IT↗

arXiv2019

Fast Deep Learning for Automatic Modulation Classification

In this work, we investigate the feasibility and effectiveness of employing deep learning algorithms for automatic recognition of the modulation type of received wireless communication signals from subsampled data. Recent work considered a GNU radio-based data set that mimics the imperfections in a real wireless channel and uses 10 different modulation types. A Convolutional Neural Network (CNN) architecture was then developed and shown to achieve performance that exceeds that of expert-based approaches. Here, we continue this line of work and investigate deep neural network architectures that deliver high classification accuracy. We identify three architectures - namely, a Convolutional Long Short-term Deep Neural Network (CLDNN), a Long Short-Term Memory neural network (LSTM), and a deep Residual Network (ResNet) - that lead to typical classification accuracy values around 90% at high SNR. We then study algorithms to reduce the training time by minimizing the size of the training data set, while incurring a minimal loss in classification accuracy. To this end, we demonstrate the performance of Principal Component Analysis in significantly reducing the training time, while maintaining good performance at low SNR. We also investigate subsampling techniques that further reduce the training time, and pave the way for online classification at high SNR. Finally, we identify representative SNR values for training each of the candidate architectures, and consequently, realize drastic reductions of the training time, with negligible loss in classification accuracy.

eess.SP↗

arXiv2018

Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approach

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based attacks: The Fast Gradient Sign attack and Fast Gradient attack. First we use an autoencoder to denoise the test data, which is trained with both clean and corrupted data. Then, we reduce the dimension of the denoised data using the hidden layer representation of another autoencoder. We perform this experiment for multiple values of the bound of adversarial perturbations, and consider different numbers of reduced dimensions. When the test data is preprocessed using this cascaded pipeline, the tested deep neural network classifier yields a much higher accuracy, thus mitigating the effect of the adversarial perturbation.

cs.LG↗

arXiv2018

Degrees of Freedom in Wireless Interference Networks with Cooperative Transmission and Backhaul Load Constraints

Degrees of freedom (DoF) gains are studied in wireless networks with cooperative transmission under a backhaul load constraint that limits the average number of messages that can be delivered from a centralized controller to base station transmitters. The backhaul load is defined as the sum of all the messages available at all the transmitters per channel use, normalized by the number of users. For Wyner's linear interference network, where each transmitter is connected to the receiver having the same index as well as one succeeding receiver, the per user DoF is characterized and the optimal scheme is presented. Furthermore, it is shown that the optimal assignment of messages to transmitters is asymmetric and satisfies a local cooperation constraint, and that the optimal coding scheme relies only on one-shot cooperative zero-forcing transmit beamforming. Using insights from the analysis of Wyner's linear interference network, the results are extended to the more practical hexagonal sectored cellular network, and coding schemes based on cooperative zero-forcing are shown to deliver significant DoF gains. It is established that by allowing for cooperative transmission and a flexible message assignment that is constrained only by an average backhaul load, one can deliver the rate gains promised by information-theoretic upper bounds with practical one-shot schemes that incur little or no additional load on the backhaul. Finally, useful upper bounds on the per user DoF for schemes based on cooperative zero-forcing are presented for lower values of the average backhaul load constraint, and an optimization framework is formulated for the general converse problem.

cs.IT↗

arXiv2018

A Blockchain Example for Cooperative Interference Management

We present an example where a distributed coordinated protocol supported by a blockchain-enabled monetary mechanism leads to achieving optimal information theoretic degrees of freedom gains. The considered setting is that of a linear interference network, where cooperative transmission is allowed, but at no cost in terms of the overall backhaul load. In other words, the average number of messages assigned to a transmitter is one. We show that a simple monetary mechanism that consists only of one coin type can enable the achievability of the optimal centralized solution. The proposed greedy distributed algorithm relies on incentivizing the users to share their resources in one channel use, in return of credit they receive for maximizing their rate gains in future channel uses. This example is the first in its class and it opens the door for constructing a unified framework for blockchain-enabled monetary mechanisms for optimal interference management and spectrum sharing.

cs.IT↗