7 February 2020 in IEEE Transactions on Network and Service Management
19 September 2017 in IEEE Access
This paper provides a comprehensive survey of content placement (CP) algorithms for cloud-based content delivery networks (CCDNs). CP algorithms are essential for content delivery for their major role in selecting content to be stored in the geographically distributed surrogate servers in the cloud to meet end-user demands with quality of service (QoS). Evidently, the key objectives of CP, i.e., cost and QoS, are competing. Cost is determined by the underlying cost model of the CCDN infrastructure while the delivered QoS is determined by where the content is placed in the CCDN. Therefore, we provide an overview of the content and the CCDN infrastructure. The overview of the content includes content characteristics and the influence of Online Social Networking on CP. The overview of the CCDN infrastructure includes elasticity and cost model, which affect CP. Our goal is to provide a holistic perspective of the aspects that impact CP algorithms and their efficiency. From the influential factors, we derive a set of design criteria for CP algorithms in CCDNs. We discuss the state-of-the-art CP algorithms for CCDNs and evaluate them against the well-motivated design criteria. We also delineate practical implications and uncover future research challenges.
10 June 2021 in IEEE Transactions on Network and Service Management
Cognitive network management is becoming quintessential to realize autonomic networking. However, the wide spread adoption of the Internet of Things (IoT) devices, increases the risk of cyber attacks. Adversaries can exploit vulnerabilities in IoT devices, which can be harnessed to launch massive Distributed Denial of Service (DDoS) attacks. Therefore, intelligent security mechanisms are needed to harden network security against these threats. In this paper, we propose Chronos, a novel time-based anomaly detection system. The anomaly detector, primarily an Autoencoder, leverages time-based features over multiple time windows to efficiently detect anomalous DDoS traffic. We develop a threshold selection heuristic that maximizes the F1-score across various DDoS attacks. Further, we compare the performance of Chronos against state-of-the-art approaches. We show that Chronos marginally outperforms another time-based system using a less complex anomaly detection pipeline, while out classing flow-based approaches with superior precision. In addition, we showcase the robustness of Chronos in the face of zero-day attacks, noise in training data, and a small number of training packets, asserting its suitability for online deployment.
29 June 2021 in IEEE Communications Surveys & Tutorials
A content delivery network (CDN) is a distributed infrastructure to deliver digital contents to end users with high performance. CDNs are critical to provide and protect the availability of Internet contents. However, adversaries can not only evade the CDN protection but also weaponize CDN resources to mount more sophisticated attacks. In this paper, we provide the first survey on CDN security. We categorize CDN security challenges per CDN infrastructure components, discuss possible countermeasures and their effectiveness, and delineate future research directions. This paper aims to highlight the state of CDN security and identify important research challenges in this area.
25 January 2021 in IEEE Transactions on Network and Service Management
Network infiltrations due to advanced persistent threats (APTs) have significantly grown in recent years. Their primary objective is to gain unauthorized access to network assets, compromise system and data. APTs are stealthy and remain dormant for an extended period of time, which makes their detection challenging. In this article, we leverage machine learning (ML) to detect hosts in a network that are a target of an APT attack. We evaluate a number of ML classifiers to detect susceptible hosts in the Los Alamos National Lab dataset. We (i) scrutinize graph-based features extracted from host authentication logs, (ii) use feature engineering to reduce dimensionality, (iii) explore balancing the training dataset using over- and under-sampling techniques, (iv) evaluate numerous supervised ML techniques and their ensemble, (v) compare our classification model to the state-of-the-art approaches that leverage the same dataset, and show that our model outperforms them with respect to prediction performance and overhead, and (vi) perturb the attack patterns to study the influence of change in attack frequency and scale on classification performance, and propose a solution for such adversarial behavior.
16 November 2022 in IEEE Transactions on Network and Service Management
5G Cloud Radio Access Networks (C-RANs) facilitate new forms of flexible resource management as dynamic RAN function splitting and placement. Virtualized RAN functions can be placed at different sites in the substrate network based on resource availability and slice constraints. Due to limited resources in the substrate network and variability in revenue of slices, the Infrastructure Provider (InP) must perform network slicing in a strategic manner, and accept or reject slice-requests to maximize long-term revenue. In this paper, we propose to use multi-agent Deep Reinforcement Learning (DRL) to jointly solve the problems of network slicing and slice Admission Control (AC). Multi-agent DRL along with reward shaping is a promising choice, which is well-suited to problems where multiple distinct tasks have to be performed optimally. The proposed DRL approach can learn the dynamics of slice-request traffic and effectively address these joint problems. We compare multi-agent DRL to approaches that use: (i) simple heuristics to address the problems, and (ii) DRL to address either slicing or AC. Our results show that the proposed approach achieves up to 30% and 5.18% gain in long-term InP revenue when compared to approaches (i) and (ii), respectively. Additionally, we show that multi-agent DRL is preferable to a single-agent DRL approach for the joint problems in terms of convergence time and InP revenue. Finally, we evaluate the robustness of the trained agents in scenarios that differ from training, such as different arrival rates and real dynamic traffic patterns.