IU Indianapolis ScholarWorks :: Browsing by Author "Durresi, Arjan"

Browsing by Author "Durresi, Arjan"

Now showing 1 - 10 of 42

Advances in Mobile Communications and Computing
(Hindawi, 2009) Durresi, Arjan; Denko, Mieso; Computer and Information Science, School of Science
Advances in Wireless Networks
(Hindawi, 2009-04-13) Durresi, Arjan; Denko, Mieso; Computer and Information Science, School of Science
Adversarial Attacks and Defense Mechanisms to Improve Robustness of Deep Temporal Point Processes
(2022-08) Khorshidi, Samira; Mohler, George; Al Hasan, Mohammad; Raje, Rajeev; Durresi, Arjan
Temporal point processes (TPP) are mathematical approaches for modeling asynchronous event sequences by considering the temporal dependency of each event on past events and its instantaneous rate. Temporal point processes can model various problems, from earthquake aftershocks, trade orders, gang violence, and reported crime patterns, to network analysis, infectious disease transmissions, and virus spread forecasting. In each of these cases, the entity’s behavior with the corresponding information is noted over time as an asynchronous event sequence, and the analysis is done using temporal point processes, which provides a means to define the generative mechanism of the sequence of events and ultimately predict events and investigate causality. Among point processes, Hawkes process as a stochastic point process is able to model a wide range of contagious and self-exciting patterns. One of Hawkes process’s well-known applications is predicting the evolution of viral processes on networks, which is an important problem in biology, the social sciences, and the study of the Internet. In existing works, mean-field analysis based upon degree distribution is used to predict viral spreading across networks of different types. However, it has been shown that degree distribution alone fails to predict the behavior of viruses on some real-world networks. Recent attempts have been made to use assortativity to address this shortcoming. This thesis illustrates how the evolution of such a viral process is sensitive to the underlying network’s structure. In Chapter 3 , we show that adding assortativity does not fully explain the variance in the spread of viruses for a number of real-world networks. We propose using the graphlet frequency distribution combined with assortativity to explain variations in the evolution of viral processes across networks with identical degree distribution. Using a data-driven approach, by coupling predictive modeling with viral process simulation on real-world networks, we show that simple regression models based on graphlet frequency distribution can explain over 95% of the variance in virality on networks with the same degree distribution but different network topologies. Our results highlight the importance of graphlets and identify a small collection of graphlets that may have the most significant influence over the viral processes on a network. Due to the flexibility and expressiveness of deep learning techniques, several neural network-based approaches have recently shown promise for modeling point process intensities. However, there is a lack of research on the possible adversarial attacks and the robustness of such models regarding adversarial attacks and natural shocks to systems. Furthermore, while neural point processes may outperform simpler parametric models on in-sample tests, how these models perform when encountering adversarial examples or sharp non-stationary trends remains unknown. In Chapter 4 , we propose several white-box and black-box adversarial attacks against deep temporal point processes. Additionally, we investigate the transferability of whitebox adversarial attacks against point processes modeled by deep neural networks, which are considered a more elevated risk. Extensive experiments confirm that neural point processes are vulnerable to adversarial attacks. Such a vulnerability is illustrated both in terms of predictive metrics and the effect of attacks on the underlying point process’s parameters. Expressly, adversarial attacks successfully transform the temporal Hawkes process regime from sub-critical to into a super-critical and manipulate the modeled parameters that is considered a risk against parametric modeling approaches. Additionally, we evaluate the vulnerability and performance of these models in the presence of non-stationary abrupt changes, using the crimes and Covid-19 pandemic dataset as an example. Considering the security vulnerability of deep-learning models, including deep temporal point processes, to adversarial attacks, it is essential to ensure the robustness of the deployed algorithms that is despite the success of deep learning techniques in modeling temporal point processes. In Chapter 5 , we study the robustness of deep temporal point processes against several proposed adversarial attacks from the adversarial defense viewpoint. Specifically, we investigate the effectiveness of adversarial training using universal adversarial samples in improving the robustness of the deep point processes. Additionally, we propose a general point process domain-adopted (GPDA) regularization, which is strictly applicable to temporal point processes, to reduce the effect of adversarial attacks and acquire an empirically robust model. In this approach, unlike other computationally expensive approaches, there is no need for additional back-propagation in the training step, and no further network isrequired. Ultimately, we propose an adversarial detection framework that has been trained in the Generative Adversarial Network (GAN) manner and solely on clean training data. Finally, in Chapter 6 , we discuss implications of the research and future research directions.
Architecture for Mobile Heterogeneous Multi Domain Networks
(Hindawi, 2010-04-01) Durresi, Arjan; Zhang, Ping; Durresi, Mimoza; Barolli, Leonard; Computer and Information Science, School of Science
Multi domain networks can be used in several scenarios including military, enterprize networks, emergency networks and many other cases. In such networks, each domain might be under its own administration. Therefore, the cooperation among domains is conditioned by individual domain policies regarding sharing information, such as network topology, connectivity, mobility, security, various service availability and so on. We propose a new architecture for Heterogeneous Multi Domain (HMD) networks, in which one the operations are subject to specific domain policies. We propose a hierarchical architecture, with an infrastructure of gateways at highest-control level that enables policy based interconnection, mobility and other services among domains. Gateways are responsible for translation among different communication protocols, including routing, signalling, and security. Besides the architecture, we discuss in more details the mobility and adaptive capacity of services in HMD. We discuss the HMD scalability and other advantages compared to existing architectural and mobility solutions. Furthermore, we analyze the dynamic availability at the control level of the hierarchy.
Control Theoretical Modeling of Trust-Based Decision Making in Food-Energy-Water Management
(Springer, 2021) Uslu, Suleyman; Kaur, Davinder; Rivera, Samuel J.; Durresi, Arjan; Babbar-Sebens, Meghna; Tilt, Jenna H.; Computer and Information Science, School of Science
We propose a hybrid Human-Machine decision making to manage Food-Energy-Water resources. In our system trust among human actors during decision making is measured and managed. Furthermore, such trust is used to pressure human actors to choose among the solutions generated by algorithms that satisfy the community’s preferred trade-offs among various objectives. We model the trust-based loops in decision making by using control theory. In this system, the feedback information is the trust pressure that actors receive from peers. Using control theory, we studied the dynamics of the trust of an actor. Then, we presented the modeling of the change of solution distances. In both scenarios, we also calculated the settling times and the stability using the transfer functions and their Z-transforms as the number of rounds to show whether and when the decision making is finalized.
Crime Detection from Pre-crime Video Analysis
(2024-05) Kilic, Sedat; Tuceryan, Mihran; Zheng, Jiang Yu; Tsechpenakis, Gavriil; Durresi, Arjan
This research investigates the detection of pre-crime events, specifically targeting behaviors indicative of shoplifting, through the advanced analysis of CCTV video data. The study introduces an innovative approach that leverages augmented human pose and emotion information within individual frames, combined with the extraction of activity information across subsequent frames, to enhance the identification of potential shoplifting actions before they occur. Utilizing a diverse set of models including 3D Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Recurrent Neural Networks (RNNs), and a specially developed transformer architecture, the research systematically explores the impact of integrating additional contextual information into video analysis. By augmenting frame-level video data with detailed pose and emotion insights, and focusing on the temporal dynamics between frames, our methodology aims to capture the nuanced behavioral patterns that precede shoplifting events. The comprehensive experimental evaluation of our models across different configurations reveals a significant improvement in the accuracy of pre-crime detection. The findings underscore the crucial role of combining visual features with augmented data and the importance of analyzing activity patterns over time for a deeper understanding of pre-shoplifting behaviors. The study’s contributions are multifaceted, including a detailed examination of pre-crime frames, strategic augmentation of video data with added contextual information, the creation of a novel transformer architecture customized for pre-crime analysis, and an extensive evaluation of various computational models to improve predictive accuracy.
Economic Analysis of Software Defined Networking (SDN) Under Various Network Failure Scenarios
(IEEE, 2019-05) Karakus, Murat; Durresi, Arjan; Computer and Information Science, School of Science
Failures are inevitable in an operational network. They can happen anytime in different sizes and components of a network. They impact the network economics regarding CAPEX (Capital Expenditure), OPEX (Operational Expenditure), revenue lost due to service provisioning cut and so on. In order to mitigate the damages resulting from these failures, reactions of network architectures and designs are crucial for the future of the network. Recently, Software Defined Networking (SDN) has got the attention of researchers from both academia and industry as a means in order to increase network availability and reliability due to features, such as centralized automated control and global network view, it promises in networking. To this end, we explore the effects of programmable network architectures, i.e. SDN technology, and traditional network architectures, i.e. MPLS (Multiprotocol Label Switching) technology, on network economics by exploiting Number of Satisfied Service Requests and our predefined Unit Service Cost Scalability metrics under network failure scenarios: i) a random single data plane link failure and ii) a random controller (i.e. control plane) failure. To the best of our knowledge, this study is the first to consider a comparison of a programmable network architecture, i.e. SDN, along with different control plane models, Centralized (Single) Control Plane (CCP), Distributed (Flat) Control Plane (DCP), and Hierarchical Control Plane (HCP), and a non-programmable network architecture, i.e. MPLS, regarding network economics in case of network failures.
Economic Impact Analysis of Control Plane Architectures in Software Defined Networking (SDN)
(IEEE, 2018-05) Karakus, Murat; Durresi, Arjan; Computer and Information Science, School of Science
Economical and operational facets of networks drive the necessity for significant changes towards fundamentals of networking architectures. Recently, the momentum of programmable networking attempts illustrates the significance of economic aspects of network technologies. Software Defined Networking (SDN) has got the attention of researchers from both academia and industry as a means to decrease network costs and generate revenue for service providers due to features it promises in networking. In this article, we perform an economic analysis of SDN about different popular SDN control plane architectures: Centralized Control Plane (CCP), Distributed Control Plane with Local View (DCP_LV), and Hierarchical Control Plane (HCP) model. In particular, we investigate the economic impact of these control plane architectures about the unit cost for a service with bandwidth QoS parameter as well as Total Cost of Ownership (TCO) and network revenue for network owners under different traffic patterns. We characterize the unit cost for a service concerning CAPEX, OPEX, and workload of a network in a certain time period and apply the calculation methods in different SDN control plane models. Our experiments and analysis show that CCP model shows the highest TCO while DCP_LV model results in lowest amount among them. In addition, HCP model shows the lowest unit cost for a service among all models while CCP gives the highest cost for the same service tier. This work aims at being a useful primer to providing insights regarding the economic impact of control plane architectures in SDN for network researchers and owners to plan their investments.
Economic Viability of Software Defined Networking (SDN)
(Elsevier, 2018-04) Karakus, Murat; Durresi, Arjan; Computer and Information Science, School of Science
Economical and operational facets of networks drive the necessity for significant changes towards fundamentals of networking architectures. Recently, the momentum of programmable networking attempts illustrates the significance of economic aspects of network technologies. Software Defined Networking (SDN) has got the attention of researchers from both academia and industry as a means to decrease network costs and generate revenue for service providers due to features it promises in networking. In this article, we investigate how programmable network architectures, i.e. SDN technology, affect the network economics compared to traditional network architectures, i.e. MPLS technology. We define two metrics, Unit Service Cost Scalability and Cost-to-Service, to evaluate how SDN architecture performs compared to MPLS architecture. Also, we present mathematical models to calculate certain cost parts of a network. In addition, we compare different popular SDN control plane models, Centralized Control Plane (CCP), Distributed Control Plane (DCP), and Hierarchical Control Plane (HCP), to understand the economic impact of them with regards to the defined metrics. We use video traffic with different patterns for the comparison. This work aims at being a useful primer to providing insights regarding which technology and control plane model are appropriate for a specific service, i.e. video, for network owners to plan their investments.
Enabling Real Time Instrumentation Using Reservoir Sampling and Binpacking
(2023-05) Meruga, Sai Pavan Kumar; Hill, James H.; Durresi, Arjan; Zheng, Jiang Yu
This thesis investigates the overhead added by reservoir sampling algorithm at different levels of granularity in real-time instrumentation of a distributed software systems. Firstly, this thesis not only discusses the inconsistencies found in the implementation of the reservoir sampling pintool in paper [ 1 ] but also provides the correct implementation. Secondly, this thesis provides the design and implementation of pintools for different level of granularities i.e., thread level, image level and routine level. Additionally, we provide quantitative comparison of performance for different sampling techniques (including reservoir sampling) at different levels of granularity. Based on the insights obtained from the empirical results, to enable real time instrumentation, we need to scale and manage the resources in the best way possible. To scale the reservoir sampling algorithm on a real time software system we integrate the traditional bin packing approach with the instrumentation in such a way that there is a decrease in the memory usage and improve the performance. The results of this research show that percentage difference between overhead added by Reservoir and Constant Sampling at a Image level granularity is 1.74%, at a Routine level granularity is 0.3% percent, at a Thread level granularity is 0.035%. Additionally, when we use bin packing technique along with reservoir sampling it normalizes the memory usage/performance runtime for Reservoir Sampling across multiple threads and different system visibility levels.

Browsing by Author "Durresi, Arjan"

Results Per Page

Sort Options