This page has only limited features, please log in for full access.
Mohiuddin Ahmed has made practical and theoretical contributions in cyber security and big data analytics for several application domains. His research has a high impact on data and security analytics, false data injection attacks, and digital health. Mohiuddin has led and edited multiple books and contributed articles in The Conversation. He has over 50 publications in reputed venues. Mohiuddin secured the prestigious ECU Early Career Researcher Grant for investigating effectiveness of blockchain for dependable and secure e-health. He also secured several external and internal grants within a very short time frame.
While anomaly detection is very important in many domains, such as in cybersecurity, there are many rare anomalies or infrequent patterns in cybersecurity datasets. Detection of infrequent patterns is computationally expensive. Cybersecurity datasets consist of many features, mostly irrelevant, resulting in lower classification performance by machine learning algorithms. Hence, a feature selection (FS) approach, i.e., selecting relevant features only, is an essential preprocessing step in cybersecurity data analysis. Despite many FS approaches proposed in the literature, cooperative co-evolution (CC)-based FS approaches can be more suitable for cybersecurity data preprocessing considering the Big Data scenario. Accordingly, in this paper, we have applied our previously proposed CC-based FS with random feature grouping (CCFSRFG) to a benchmark cybersecurity dataset as the preprocessing step. The dataset with original features and the dataset with a reduced number of features were used for infrequent pattern detection. Experimental analysis was performed and evaluated using 10 unsupervised anomaly detection techniques. Therefore, the proposed infrequent pattern detection is termed Unsupervised Infrequent Pattern Detection (UIPD). Then, we compared the experimental results with and without FS in terms of true positive rate (TPR). Experimental analysis indicates that the highest rate of TPR improvement was by cluster-based local outlier factor (CBLOF) of the backdoor infrequent pattern detection, and it was 385.91% when using FS. Furthermore, the highest overall infrequent pattern detection TPR was improved by 61.47% for all infrequent patterns using clustering-based multivariate Gaussian outlier score (CMGOS) with FS.
A. Rashid; Mohiuddin Ahmed; Al-Sakib Pathan. Infrequent Pattern Detection for Reliable Network Traffic Analysis Using Robust Evolutionary Computation. Sensors 2021, 21, 3005 .
AMA StyleA. Rashid, Mohiuddin Ahmed, Al-Sakib Pathan. Infrequent Pattern Detection for Reliable Network Traffic Analysis Using Robust Evolutionary Computation. Sensors. 2021; 21 (9):3005.
Chicago/Turabian StyleA. Rashid; Mohiuddin Ahmed; Al-Sakib Pathan. 2021. "Infrequent Pattern Detection for Reliable Network Traffic Analysis Using Robust Evolutionary Computation." Sensors 21, no. 9: 3005.
The efficiency of cooperative communication protocols to increase the reliability and range of transmission for Vehicular Ad hoc Network (VANET) is proven, but identity verification and communication security are required to be ensured. Though it is difficult to maintain strong network connections between vehicles because of there high mobility, with the help of cooperative communication, it is possible to increase the communication efficiency, minimise delay, packet loss, and Packet Dropping Rate (PDR). However, cooperating with unknown or unauthorized vehicles could result in information theft, privacy leakage, vulnerable to different security attacks, etc. In this paper, a blockchain based secure and privacy preserving authentication protocol is proposed for the Internet of Vehicles (IoV). Blockchain is utilized to store and manage the authentication information in a distributed and decentralized environment and developed on the Ethereum platform that uses a digital signature algorithm to ensure confidentiality, non-repudiation, integrity, and preserving the privacy of the IoVs. For optimized communication, transmitted services are categorized into emergency and optional services. Similarly, to optimize the performance of the authentication process, IoVs are categorized as emergency and general IoVs. The proposed cooperative protocol is validated by numerical analyses which show that the protocol successfully increases the system throughput and decreases PDR and delay. On the other hand, the authentication protocol requires minimum storage as well as generates low computational overhead that is suitable for the IoVs with limited computer resources.
A. Akhter; Mohiuddin Ahmed; A. Shah; Adnan Anwar; A. Kayes; Ahmet Zengin. A Blockchain-Based Authentication Protocol for Cooperative Vehicular Ad Hoc Network. Sensors 2021, 21, 1273 .
AMA StyleA. Akhter, Mohiuddin Ahmed, A. Shah, Adnan Anwar, A. Kayes, Ahmet Zengin. A Blockchain-Based Authentication Protocol for Cooperative Vehicular Ad Hoc Network. Sensors. 2021; 21 (4):1273.
Chicago/Turabian StyleA. Akhter; Mohiuddin Ahmed; A. Shah; Adnan Anwar; A. Kayes; Ahmet Zengin. 2021. "A Blockchain-Based Authentication Protocol for Cooperative Vehicular Ad Hoc Network." Sensors 21, no. 4: 1273.
Existing research shows that Cluster-based Medium Access Control (CB-MAC) protocols perform well in controlling and managing Vehicular Ad hoc Network (VANET), but requires ensuring improved security and privacy preserving authentication mechanism. To this end, we propose a multi-level blockchain-based privacy-preserving authentication protocol. The paper thoroughly explains the formation of the authentication centers, vehicles registration, and key generation processes. In the proposed architecture, a global authentication center (GAC) is responsible for storing all vehicle information, while Local Authentication Center (LAC) maintains a blockchain to enable quick handover between internal clusters of vehicle. We also propose a modified control packet format of IEEE 802.11 standards to remove the shortcomings of the traditional MAC protocols. Moreover, cluster formation, membership and cluster-head selection, and merging and leaving processes are implemented while considering the safety and non-safety message transmission to increase the performance. All blockchain communication is performed using high speed 5G internet while encrypted information is transmitted while using the RSA-1024 digital signature algorithm for improved security, integrity, and confidentiality. Our proof-of-concept implements the authentication schema while considering multiple virtual machines. With detailed experiments, we show that the proposed method is more efficient in terms of time and storage when compared to the existing methods. Besides, numerical analysis shows that the proposed transmission protocols outperform traditional MAC and benchmark methods in terms of throughput, delay, and packet dropping rate.
A. Akhter; Mohiuddin Ahmed; A. Shah; Adnan Anwar; Ahmet Zengin. A Secured Privacy-Preserving Multi-Level Blockchain Framework for Cluster Based VANET. Sustainability 2021, 13, 400 .
AMA StyleA. Akhter, Mohiuddin Ahmed, A. Shah, Adnan Anwar, Ahmet Zengin. A Secured Privacy-Preserving Multi-Level Blockchain Framework for Cluster Based VANET. Sustainability. 2021; 13 (1):400.
Chicago/Turabian StyleA. Akhter; Mohiuddin Ahmed; A. Shah; Adnan Anwar; Ahmet Zengin. 2021. "A Secured Privacy-Preserving Multi-Level Blockchain Framework for Cluster Based VANET." Sustainability 13, no. 1: 400.
Cybersecurity issues constitute a key concern of today’s technology-based economies. Cybersecurity has become a core need for providing a sustainable and safe society to online users in cyberspace. Considering the rapid increase of technological implementations, it has turned into a global necessity in the attempt to adapt security countermeasures, whether direct or indirect, and prevent systems from cyberthreats. Identifying, characterizing, and classifying such threats and their sources is required for a sustainable cyber-ecosystem. This paper focuses on the cybersecurity of smart grids and the emerging trends such as using blockchain in the Internet of Things (IoT). The cybersecurity of emerging technologies such as smart cities is also discussed. In addition, associated solutions based on artificial intelligence and machine learning frameworks to prevent cyber-risks are also discussed. Our review will serve as a reference for policy-makers from the industry, government, and the cybersecurity research community.
Shahrin Sadik; Mohiuddin Ahmed; Leslie F. Sikos; A. K. M. Najmul Islam. Toward a Sustainable Cybersecurity Ecosystem. Computers 2020, 9, 74 .
AMA StyleShahrin Sadik, Mohiuddin Ahmed, Leslie F. Sikos, A. K. M. Najmul Islam. Toward a Sustainable Cybersecurity Ecosystem. Computers. 2020; 9 (3):74.
Chicago/Turabian StyleShahrin Sadik; Mohiuddin Ahmed; Leslie F. Sikos; A. K. M. Najmul Islam. 2020. "Toward a Sustainable Cybersecurity Ecosystem." Computers 9, no. 3: 74.
The rapid progress of modern technologies generates a massive amount of high-throughput data, called Big Data, which provides opportunities to find new insights using machine learning (ML) algorithms. Big Data consist of many features (also called attributes); however, not all these are necessary or relevant, and they may degrade the performance of ML algorithms. Feature selection (FS) is an essential preprocessing step to reduce the dimensionality of a dataset. Evolutionary algorithms (EAs) are widely used search algorithms for FS. Using classification accuracy as the objective function for FS, EAs, such as the cooperative co-evolutionary algorithm (CCEA), achieve higher accuracy, even with a higher number of features. Feature selection has two purposes: reducing the number of features to decrease computations and improving classification accuracy, which are contradictory but can be achieved using a single objective function. For this very purpose, this paper proposes a penalty-based wrapper objective function. This function can be used to evaluate the FS process using CCEA, hence called Cooperative Co-Evolutionary Algorithm-Based Feature Selection (CCEAFS). An experiment was performed using six widely used classifiers on six different datasets from the UCI ML repository with FS and without FS. The experimental results indicate that the proposed objective function is efficient at reducing the number of features in the final feature subset without significantly reducing classification accuracy. Based on different performance measures, in most cases, naïve Bayes outperforms other classifiers when using CCEAFS.
A. N. M. Bazlur Rashid; Mohiuddin Ahmed; Leslie F. Sikos; Paul Haskell-Dowland. A Novel Penalty-Based Wrapper Objective Function for Feature Selection in Big Data Using Cooperative Co-Evolution. IEEE Access 2020, 8, 150113 -150129.
AMA StyleA. N. M. Bazlur Rashid, Mohiuddin Ahmed, Leslie F. Sikos, Paul Haskell-Dowland. A Novel Penalty-Based Wrapper Objective Function for Feature Selection in Big Data Using Cooperative Co-Evolution. IEEE Access. 2020; 8 ():150113-150129.
Chicago/Turabian StyleA. N. M. Bazlur Rashid; Mohiuddin Ahmed; Leslie F. Sikos; Paul Haskell-Dowland. 2020. "A Novel Penalty-Based Wrapper Objective Function for Feature Selection in Big Data Using Cooperative Co-Evolution." IEEE Access 8, no. : 150113-150129.
The k-means clustering algorithm is considered one of the most powerful and popular data mining algorithms in the research community. However, despite its popularity, the algorithm has certain limitations, including problems associated with random initialization of the centroids which leads to unexpected convergence. Additionally, such a clustering algorithm requires the number of clusters to be defined beforehand, which is responsible for different cluster shapes and outlier effects. A fundamental problem of the k-means algorithm is its inability to handle various data types. This paper provides a structured and synoptic overview of research conducted on the k-means algorithm to overcome such shortcomings. Variants of the k-means algorithms including their recent developments are discussed, where their effectiveness is investigated based on the experimental analysis of a variety of datasets. The detailed experimental analysis along with a thorough comparison among different k-means clustering algorithms differentiates our work compared to other existing survey papers. Furthermore, it outlines a clear and thorough understanding of the k-means algorithm along with its different research directions.
Mohiuddin Ahmed; Raihan Seraj; Syed Mohammed Shamsul Islam. The k-means Algorithm: A Comprehensive Survey and Performance Evaluation. Electronics 2020, 9, 1295 .
AMA StyleMohiuddin Ahmed, Raihan Seraj, Syed Mohammed Shamsul Islam. The k-means Algorithm: A Comprehensive Survey and Performance Evaluation. Electronics. 2020; 9 (8):1295.
Chicago/Turabian StyleMohiuddin Ahmed; Raihan Seraj; Syed Mohammed Shamsul Islam. 2020. "The k-means Algorithm: A Comprehensive Survey and Performance Evaluation." Electronics 9, no. 8: 1295.
The term “concept drift” refers to a change in statistical distribution of the data. In machine learning and predictive analysis, a fundamental assumption exits which reasons that the data is a random variable which is being generated independently from an underlying stationary distribution. In this chapter we present discussions on concept drifts that are inherent in the context big data. We discuss different forms of concept drifts that are evident in streaming data and outline different techniques for handling them. Handling concept drift is important for big data where the data flow occurs continuously causing existing learned models to lose their predictive accuracy. This chapter will serve as a reference to academicians and industry practitioners who are interested in the niche area of handling concept drift for big data applications.
Raihan Seraj; Mohiuddin Ahmed. Concept Drift for Big Data. Cyberspace 2020, 29 -43.
AMA StyleRaihan Seraj, Mohiuddin Ahmed. Concept Drift for Big Data. Cyberspace. 2020; ():29-43.
Chicago/Turabian StyleRaihan Seraj; Mohiuddin Ahmed. 2020. "Concept Drift for Big Data." Cyberspace , no. : 29-43.
Blockchain technology claims to provide unparalleled security and data privacy, yet some vulnerabilities have recently been identified. In this article, we showcase the key advantages of blockchain technology and look at recent security breaches, critically analyzing its benefits while highlighting some resulting financial mishaps.
Mohiuddin Ahmed; Al-Sakib Khan Pathan. Blockchain: Can It Be Trusted? Computer 2020, 53, 31 -35.
AMA StyleMohiuddin Ahmed, Al-Sakib Khan Pathan. Blockchain: Can It Be Trusted? Computer. 2020; 53 (4):31-35.
Chicago/Turabian StyleMohiuddin Ahmed; Al-Sakib Khan Pathan. 2020. "Blockchain: Can It Be Trusted?" Computer 53, no. 4: 31-35.
In this paper, we investigate the literature around deep learning to identify its usefulness in different application domains. Our paper identifies that the effectiveness of deep learning is highly visible in the medical imaging area. Other application domains are yet to make any significant progress using deep learning. Therefore, we conclude that deep learning is a good solution for medical imaging analysis. However, its benefits are yet to be realized in other domains and researchers are pursuing to explore its effectiveness to solve problems in these domains. Our initial critical evaluation suggests that deep learning may be a hype in most domains. In order to probe this further, we call for a deeper engagement with prior literature in different application domains of deep learning.
Mohiuddin Ahmed; A. K. M. Najmul Islam. Deep Learning: Hope or Hype. Annals of Data Science 2020, 7, 427 -432.
AMA StyleMohiuddin Ahmed, A. K. M. Najmul Islam. Deep Learning: Hope or Hype. Annals of Data Science. 2020; 7 (3):427-432.
Chicago/Turabian StyleMohiuddin Ahmed; A. K. M. Najmul Islam. 2020. "Deep Learning: Hope or Hype." Annals of Data Science 7, no. 3: 427-432.
The advances in information and communication technology are consistently beneficial for the healthcare sector. A trend in the healthcare sector is the progressive shift in how data are acquired and the storage of such data in different facilities, such as in the cloud, due to the efficiency and effectiveness offered. Digital images related to healthcare are sensitive in nature and require maximum security and privacy. A malicious entity can tamper with such stored digital images to mislead healthcare personnel and the consequences of wrong diagnosis are harmful for both parties. A new type of cyber attack, a false image injection attack (FIIA) is introduced in this paper. Existing image tampering detection measures are unable to guarantee tamper-proof medical data in real time. Inspired by the effectiveness of emerging blockchain technology, a security framework, image chain (iChain) is proposed in this paper to ensure the security and privacy of the sensitive healthcare images. The practical challenges associated with the proposed framework and further research that is required are also highlighted.
Mohiuddin Ahmed. False Image Injection Prevention Using iChain. Applied Sciences 2019, 9, 4328 .
AMA StyleMohiuddin Ahmed. False Image Injection Prevention Using iChain. Applied Sciences. 2019; 9 (20):4328.
Chicago/Turabian StyleMohiuddin Ahmed. 2019. "False Image Injection Prevention Using iChain." Applied Sciences 9, no. 20: 4328.
This paper explores the Agile methodologies, Scrum and Kanban, to define their advantages and limitations of use. The methods are compared for their use in software development, specifying which would be a suitable option for a game development process focusing on maximizing productivity and quality of the software. Exploration of use cases and methodology guides are discussed, defining the benefits of choosing Kanban or Scrum for a software development team. Findings show Scrum to be a method that focuses on the verbal communication through sprint meetings and reviews. Kanban is described as a visually driven framework that utilizes a Kanban board and cards for communication. Scrum is a strict method can only implement change after a sprint, while Kanban is more flexible and can make changes at any point in the development process. A hybrid of the two methods, Scrumban, is also investigated and found to be an alternative for users who find aspects of both methodologies to be appropriate for their team. There is a great deal of consideration required for independent game developers as they need to reflect on their team dynamics and situation before determining which methodology is best suited for them.
Renae Aurisch; Mohiuddin Ahmed; Abu Barkat. An outlook at Agile methodologies for the independent games developer. International Journal of Computers and Applications 2019, 1 -7.
AMA StyleRenae Aurisch, Mohiuddin Ahmed, Abu Barkat. An outlook at Agile methodologies for the independent games developer. International Journal of Computers and Applications. 2019; ():1-7.
Chicago/Turabian StyleRenae Aurisch; Mohiuddin Ahmed; Abu Barkat. 2019. "An outlook at Agile methodologies for the independent games developer." International Journal of Computers and Applications , no. : 1-7.
Identifying interesting patterns from huge amount of data is a challenging task across a wide rage of application domain. Especially, for cyber security being able to identify rare types of network activities or anomalies from network traffic data (aka Big Data!) is an important but time consuming data analysis task having moderate computing resources. Existing research has shown that it is possible to detect rare anomalies from the summarized version of big data. Therefore, summarization is an effective preprocessing function before applying anomaly detection techniques. This aim of this paper is to improve and quantify the scalability and accuracy of the anomaly detection techniques by using summarization. Hence, we propose a sampling based summarization technique (SUCh: Summarization Using Chernoff-Bound) which is computationally effective than the existing techniques and also performs better in identifying rare anomalies from twelve benchmark network traffic datasets. Experimental results show that, instead of using original dataset, a summary of the data yields better performance in terms of true positive and false positive rates, when used for anomaly detection with less time required.
Mohiuddin Ahmed. Intelligent Big Data Summarization for Rare Anomaly Detection. IEEE Access 2019, 7, 68669 -68677.
AMA StyleMohiuddin Ahmed. Intelligent Big Data Summarization for Rare Anomaly Detection. IEEE Access. 2019; 7 (99):68669-68677.
Chicago/Turabian StyleMohiuddin Ahmed. 2019. "Intelligent Big Data Summarization for Rare Anomaly Detection." IEEE Access 7, no. 99: 68669-68677.
The current healthcare sector is facing difficulty in satisfying the growing issues, expenses, and heavy regulation of quality treatment. Surely, electronic medical records (EMRs) and protected health information (PHI) are highly sensitive, personally identifiable information (PII). However, the sharing of EMRs, enhances overall treatment quality. A distributed ledger (blockchain) technology, embedded with privacy and security by architecture, provides a transparent application developing platform. Privacy, security, and lack of confidence among stakeholders are the main downsides of extensive medical collaboration. This study, therefore, utilizes the transparency, security, and efficiency of blockchain technology to establish a collaborative medical decision-making scheme. This study considers the experience, skill, and collaborative success rate of four key stakeholders (patient, cured patient, doctor, and insurance company) in the healthcare domain to propose a local reference-based consortium blockchain scheme, and an associated consensus gathering algorithm, proof-of-familiarity (PoF). Stakeholders create a transparent and tenable medical decision to increase the interoperability among collaborators through PoF. A prototype of PoF is tested with multichain 2.0, a blockchain implementing framework. Moreover, the privacy of identities, EMRs, and decisions are preserved by two-layer storage, encryption, and a timestamp storing mechanism. Finally, superiority over existing schemes is identified to improve personal data (PII) privacy and patient-centric outcomes research (PCOR).
Jinhong Yang; Mehedi Hassan Onik; Nam-Yong Lee; Mohiuddin Ahmed; Chul-Soo Kim. Proof-of-Familiarity: A Privacy-Preserved Blockchain Scheme for Collaborative Medical Decision-Making. Applied Sciences 2019, 9, 1370 .
AMA StyleJinhong Yang, Mehedi Hassan Onik, Nam-Yong Lee, Mohiuddin Ahmed, Chul-Soo Kim. Proof-of-Familiarity: A Privacy-Preserved Blockchain Scheme for Collaborative Medical Decision-Making. Applied Sciences. 2019; 9 (7):1370.
Chicago/Turabian StyleJinhong Yang; Mehedi Hassan Onik; Nam-Yong Lee; Mohiuddin Ahmed; Chul-Soo Kim. 2019. "Proof-of-Familiarity: A Privacy-Preserved Blockchain Scheme for Collaborative Medical Decision-Making." Applied Sciences 9, no. 7: 1370.
In this paper, we investigated the current scenario of big data project management followed by success criteria. Our research found that, the evaluation metrics are generic and no universal metric available for the big data projects. Therefore, we have proposed few evaluation metrics suitable for big data projects.
Munir Ahmad Saeed; Mohiuddin Ahmed. Evaluation Metrics for Big Data Project Management. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018, 139 -142.
AMA StyleMunir Ahmad Saeed, Mohiuddin Ahmed. Evaluation Metrics for Big Data Project Management. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. 2018; ():139-142.
Chicago/Turabian StyleMunir Ahmad Saeed; Mohiuddin Ahmed. 2018. "Evaluation Metrics for Big Data Project Management." Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering , no. : 139-142.
Internet of Things (IoT) facilitates networking among different types of electronic devices. The emerging false data injection attacks (FDIAs) have drawn attention and heavily researched in power systems and smart grid. The cyber criminals compromise a networked device and inject data. However, these attacks on IoT may lead to significant losses and able to disrupt normal activities among the devices in any IoT network. To the best of our knowledge, there is not enough substantial investigation on FDIA in IoT. Therefore, in this chapter, the impact of FDIA is analyzed from IoT perspective and the usefulness of existing FDIA countermeasures is investigated. The key contribution of this chapter is to create a new direction of IoT research on FDIA detection and prevention. The chapter will be beneficial for graduate level students, academicians, and researchers in this application domain.
Biozid Bostami; Mohiuddin Ahmed; Salimur Choudhury. False Data Injection Attacks in Internet of Things. Edge Computing 2018, 47 -58.
AMA StyleBiozid Bostami, Mohiuddin Ahmed, Salimur Choudhury. False Data Injection Attacks in Internet of Things. Edge Computing. 2018; ():47-58.
Chicago/Turabian StyleBiozid Bostami; Mohiuddin Ahmed; Salimur Choudhury. 2018. "False Data Injection Attacks in Internet of Things." Edge Computing , no. : 47-58.
A summarization technique creates a concise version of large amount of data (big data!) which reduces the computational cost of analysis and decision-making. There are interesting data patterns, such as rare anomalies, which are more infrequent in nature than other data instances. For example, in smart healthcare environment, the proportion of infrequent patterns is very low in the underlying cyber physical system (CPS). Existing summarization techniques overlook the issue of representing such interesting infrequent patterns in a summary. In this paper, a novel clustering-based technique is proposed which uses an information theoretic measure to identify the infrequent frequent patterns for inclusion in a summary. The experiments conducted on seven benchmark CPS datasets show substantially good results in terms of including the infrequent patterns in summaries than existing techniques.
Mohiuddin Ahmed; Abu Barkat Ullah. Infrequent pattern mining in smart healthcare environment using data summarization. The Journal of Supercomputing 2018, 74, 5041 -5059.
AMA StyleMohiuddin Ahmed, Abu Barkat Ullah. Infrequent pattern mining in smart healthcare environment using data summarization. The Journal of Supercomputing. 2018; 74 (10):5041-5059.
Chicago/Turabian StyleMohiuddin Ahmed; Abu Barkat Ullah. 2018. "Infrequent pattern mining in smart healthcare environment using data summarization." The Journal of Supercomputing 74, no. 10: 5041-5059.
Summarization has been proven to be a useful and effective technique supporting data analysis of large amounts of data. Knowledge discovery from data (KDD) is time consuming, and summarization is an important step to expedite KDD tasks by intelligently reducing the size of processed data. In this paper, different summarization techniques for structured and unstructured data are discussed. The key finding of this survey is that not all summarization techniques create a summary suitable for further analysis. It is highlighted that sampling techniques are a viable way of creating a summary for further knowledge discovery such as anomaly detection from summary. Also different summary evaluation metrics are discussed.
Mohiuddin Ahmed. Data summarization: a survey. Knowledge and Information Systems 2018, 58, 249 -273.
AMA StyleMohiuddin Ahmed. Data summarization: a survey. Knowledge and Information Systems. 2018; 58 (2):249-273.
Chicago/Turabian StyleMohiuddin Ahmed. 2018. "Data summarization: a survey." Knowledge and Information Systems 58, no. 2: 249-273.
In certain cyber-attack scenarios, such as flooding denial of service attacks, the data distribution changes significantly. This forms a collective anomaly, where some similar kinds of normal data instances appear in abnormally large numbers. Since they are not rare anomalies, existing anomaly detection techniques cannot properly identify them. This paper investigates detecting this behaviour using the existing clustering and co-clustering based techniques and utilizes the network traffic modelling technique via Hurst parameter to propose a more effective algorithm combining clustering and Hurst parameter. Experimental analysis reflects that the proposed Hurst parameter-based technique outperforms existing collective and rare anomaly detection techniques in terms of detection accuracy and false positive rates. The experimental results are based on benchmark datasets such as KDD Cup 1999 and UNSW-NB15 datasets.
Mohiuddin Ahmed. Collective Anomaly Detection Techniques for Network Traffic Analysis. Annals of Data Science 2018, 5, 497 -512.
AMA StyleMohiuddin Ahmed. Collective Anomaly Detection Techniques for Network Traffic Analysis. Annals of Data Science. 2018; 5 (4):497-512.
Chicago/Turabian StyleMohiuddin Ahmed. 2018. "Collective Anomaly Detection Techniques for Network Traffic Analysis." Annals of Data Science 5, no. 4: 497-512.
Summarization is an important intermediate step for expediting knowledge discovery tasks such as anomaly detection. In the context of anomaly detection from data stream, the summary needs to represent both anomalous and normal data. But streaming data has distinct characteristics, such as one-pass constraint, for which conducting data mining operations are difficult. Existing stream summarization techniques are unable to create summary which represent both normal and anomalous instances. To address this problem, in this paper, a number of hybrid summarization techniques are designed and developed using the concept of reservoir for anomaly detection from network traffic. Experimental results on thirteen benchmark data streams show that the summaries produced from stream using pairwise distance (PSSR) and template matching (TMSSR) techniques can retain more anomalies than existing stream summarization techniques, and anomaly detection technique can identify the anomalies with high true positive and low false positive rate.
Mohiuddin Ahmed. Reservoir-based network traffic stream summarization for anomaly detection. Pattern Analysis and Applications 2017, 21, 579 -599.
AMA StyleMohiuddin Ahmed. Reservoir-based network traffic stream summarization for anomaly detection. Pattern Analysis and Applications. 2017; 21 (2):579-599.
Chicago/Turabian StyleMohiuddin Ahmed. 2017. "Reservoir-based network traffic stream summarization for anomaly detection." Pattern Analysis and Applications 21, no. 2: 579-599.
Mohiuddin Ahmed. An Unsupervised Approach of Knowledge Discovery from Big Data in Social Network. ICST Transactions on Scalable Information Systems 2017, 4, 1 .
AMA StyleMohiuddin Ahmed. An Unsupervised Approach of Knowledge Discovery from Big Data in Social Network. ICST Transactions on Scalable Information Systems. 2017; 4 (14):1.
Chicago/Turabian StyleMohiuddin Ahmed. 2017. "An Unsupervised Approach of Knowledge Discovery from Big Data in Social Network." ICST Transactions on Scalable Information Systems 4, no. 14: 1.