Distributed Denial of Service detection using hybrid machine learning technique

Barati, Mehdi; Abdullah, Azizol; Udzir, Nur Izura; Mahmod, Ramlan; Mustapha, Norwati

doi:10.1109/isbast.2014.7013133

Cited by 36 publications

(19 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As it has been highlighted in [60,47,46,49,39,40,41], bio/nature-inspired algorithms have been used for feature reduction in an attempt to reduce the overall compexity of detection algorithms without affecting their accuracy. For finding an optimal set of features, we have used the available nature-inspired algorithms provided from Weka toolkit.…”

Section: Experiments Results Analysismentioning

confidence: 99%

“…Dr. 95% GA [37] KDD99 Attacks 90% GA [38] KDD99 Attacks 97.57% GA & FL [39] KDD99 Attacks 95% GA & FL [40] KDD99 Attacks 95% and 1% FPR GA & FL [41] KDD99 Attacks 99.75% FL [42] Jamming DoS 99.75% ACO [43] UDP DoS 80% ACO [44] Low-rate DoS 89% ACO [45] KDD99 Attacks 96.94% ABC & ANN [46] KDD99 Attacks less 0.025 squar er. GA & ANN [49] KDD99 Attacks 99.997% DR and 0.002% FPR ANN [50] KDD99 Attacks 99.723% DR and 0.277% FPR ANN [51] NSL-KDD Attacks 96.6% DR and 3.4% FPR ANN [52] KDD99 Attacks False Accept. less 8% & False Rej.…”

Section: Discussionmentioning

confidence: 99%

“…In [49], the authors have combined the GA along with ANN, attempting to increase the detection rate. The have used the Center for Applied Internet Data Analysis (CAIDA) dataset.…”

Section: Artificial Neural Network Studiesmentioning

confidence: 99%

See 2 more Smart Citations

Bio/nature-inspired algorithms in A.I. for malicious activity detection

Procopiou

Komninos

2019

Nature-Inspired Cyber Security and Resiliency: Fundamentals, Techniques and Applications

View full text Add to dashboard Cite

Malicious software [1] is one of the main threats to networks and its assets, as well as individual users. As we approach the Internet of Things and Cyber-Physical Systems era, network traffic becomes more complex and heterogeneous. In recent years, the number of devices connected to the Internet is increased exponentially as well as big data that is produced from them. Also, each device comes with its own protocols and standards. Furthermore, computing devices operate with different protocols and standards and effective traffic monitoring becomes harder. Hence, adversaries conduct more sophisticated attacks against networks so the malicious behaviour can be more difficult to be detected. Simplistic and one-dimensional security countermeasures are likely to fail under such circumstances. Artificial intelligence and particularly learning algorithms seems to be appropriate for detecting cyber attacks. Using machine learning, fast and accurate detection of malicious behaviour is more achievable than ever. A special branch of machine learning algorithms includes nature and bio inspired algorithms. Such algorithms followed models from nature, biology, social systems and life sciences. Some examples include genetic algorithms, swarm intelligence, artificial immune systems, evolutionary algorithms, artificial neural networks, fractal geometry, chaos theory and so on [2]. Nature/Bio-inspired algorithms have an advantage against traditional machine learning algorithms, they focus on optimisation. In detail, nature acts as a method of making something as perfect as possible or choosing the most fitted samples from a population. In practice, this family of algorithms applies these principles in the form of optimisation and finding the best solution to the problem assigned. In anomaly detection, the main objective is to identify the malicious behaviour so these algorithms use their best-fit mechanisms to detect malicious abnormalities. Another beneficial usage of nature/bio inspired algorithms is to optimise the potential features used in attacks detection. An optimal set of features is selected for efficient malware detec

show abstract

Section: Experiments Results Analysismentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Bio/nature-inspired algorithms in A.I. for malicious activity detection

Procopiou

Komninos

2019

Nature-Inspired Cyber Security and Resiliency: Fundamentals, Techniques and Applications

View full text Add to dashboard Cite

show abstract

“…In the study performed by Barati et al [15], by using a machine learning technique composed of genetic algorithm and artificial neural network, it is shown that the accuracy of DDoS attack detection is improved. Yu et al [16] guaranteed the quality of service for legitimate users by using a dynamic resource allocation strategy to confront DDoS attacks that target individual cloud customers.…”

Section: Literature Overviewmentioning

confidence: 99%

Hybrid Intrusion Detection System for DDoS Attacks

Cepheli

Büyükçorak

Kurt

2016

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Distributed denial-of-service (DDoS) attacks are one of the major threats and possibly the hardest security problem for today's Internet. In this paper we propose a hybrid detection system, referred to as hybrid intrusion detection system (H-IDS), for detection of DDoS attacks. Our proposed detection system makes use of both anomaly-based and signature-based detection methods separately but in an integrated fashion and combines the outcomes of both detectors to enhance the overall detection accuracy. We apply two distinct datasets to our proposed system in order to test the detection performance of H-IDS and conclude that the proposed hybrid system gives better results than the systems based on nonhybrid detection.

show abstract

“…The work of Arun Raj Kumar and Selvakumar focuses on the identification of high rate flooding attack with high detection accuracy and fewer false alarms using adaptive and hybrid neuro-fuzzy systems with Adaptive Neuro-Fuzzy Systems (ANFIS) as a base classifier [10]. It is also worth noticing the improved performance of hybrid GA and ANN over GA and SVM [11], [12] and fusion IDS [13], [14] over individual IDSs.…”

Section: A Machine Learning Algorithms In Detecting Ddos Attacksmentioning

confidence: 99%

Ranking of machine learning algorithms based on the performance in classifying DDoS attacks

Robinson

Thomas²

2015

2015 IEEE Recent Advances in Intelligent Computational Systems (RAICS)

View full text Add to dashboard Cite

Network Security has become one of the most important factors to consider as the Internet evolves. The most important attack which affects the availability of service is Distributed Denial of Service. The service disruption may cause substantial financial loss as well as damage to the concerned network system. The traffic patterns exhibited by the DDoS affected traffic can be effectively captured by machine learning algorithms. This paper gives an evaluation and ranking of some of the supervised machine learning algorithms with the aim of reducing type I and type II errors, increasing precision and recall while maintaining detection accuracy. The performance evaluation is done using Multi Criteria Decision Aid software called Visual PROMETHEE. This work demonstrates the effectiveness of ensemble based classifiers especially the ensemble algorithm of Adaboost with Random Forest as the base classifier. Publicly available datasets such as DARPA scenario specific dataset, CAIDA DDoS Attack 2007 and CAIDA Conficker are used to evaluate the algorithms.

show abstract

Distributed Denial of Service detection using hybrid machine learning technique

Cited by 36 publications

References 13 publications

Bio/nature-inspired algorithms in A.I. for malicious activity detection

Bio/nature-inspired algorithms in A.I. for malicious activity detection

Hybrid Intrusion Detection System for DDoS Attacks

Ranking of machine learning algorithms based on the performance in classifying DDoS attacks

Contact Info

Product

Resources

About