Hybrid Deep Learning Model for Real-Time Detection of Distributed Denial of Service Attacks in Software Defined Networks

The growth of network devices has brought a lot of problems in managing the networks. The ill-managed networks create different vulnerabilities which attackers can exploit. The attackers take advantage of open-source tools and low-priced Internet to use the networks. Software Defined Networking (SDN) is a good networking architecture that can be managed centrally. The decoupled SDN architecture has the flexibility of programming network devices from the central controller. There is no doubt that SDN addresses the problem of network management; however, SDN comes with a security concern. SDN controller has a vulnerability of a single point of failure. This vulnerability makes the controller vulnerable to different network attacks, including Distributed Denial of Service (DDoS) attacks, among others. To get the best out of SDN, the controller needs security that can protect it from cyber-attacks. The Deep Learning (DL) approach enhanced the selection of the relevant features from the dataset for classification in an unsupervised manner. This paper proposed the hybrid DL model that utilises Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for DDoS attack detection. The proposed hybrid model produced a detection accuracy of 99.72%.

[1]  Gozde Karatas,et al.  Deep Learning in Intrusion Detection Systems , 2018, 2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT).

[2]  Nikolaj Goranin,et al.  Evaluation of Deep Learning Methods Efficiency for Malicious and Benign System Calls Classification on the AWSCTD , 2019, Secur. Commun. Networks.

[3]  Sina Hojjatinia,et al.  Android Botnet Detection using Convolutional Neural Networks , 2019, 2020 28th Iranian Conference on Electrical Engineering (ICEE).

[4]  P SomanK.,et al.  A short review on Applications of Deep learning for Cyber security , 2018, ArXiv.

[5]  Naveen K. Chilamkurti,et al.  Distributed attack detection scheme using deep learning approach for Internet of Things , 2017, Future Gener. Comput. Syst..

[6]  Mounir Ghogho,et al.  Intrusion Detection in SDN-Based Networks: Deep Recurrent Neural Network Approach , 2019, Deep Learning Applications for Cyber Security.

[7]  Kim-Kwang Raymond Choo,et al.  A Deep CNN Ensemble Framework for Efficient DDoS Attack Detection in Software Defined Networks , 2020, IEEE Access.

[8]  Basil S. Maglaris,et al.  Mitigation of Multi-vector Network Attacks via Orchestration of Distributed Rule Placement , 2019, 2019 IFIP/IEEE Symposium on Integrated Network and Service Management (IM).

[9]  Lisandro Zambenedetti Granville,et al.  ATLANTIC: A framework for anomaly traffic detection, classification, and mitigation in SDN , 2016, NOMS.

[10]  Yuefei Zhu,et al.  A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks , 2017, IEEE Access.

[11]  Xiaolin Li,et al.  Detection and defense of DDoS attack–based on deep learning in OpenFlow‐based SDN , 2018, Int. J. Commun. Syst..

[12]  Nei Kato,et al.  State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems , 2017, IEEE Communications Surveys & Tutorials.

[13]  Hüseyin Polat,et al.  Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models , 2020, Sustainability.

[14]  Samrat Kumar Dey,et al.  Flow Based Anomaly Detection in Software Defined Networking: A Deep Learning Approach With Feature Selection Method , 2018, 2018 4th International Conference on Electrical Engineering and Information & Communication Technology (iCEEiCT).

[15]  Po-Ching Lin,et al.  An Unsupervised Deep Learning Model for Early Network Traffic Anomaly Detection , 2020, IEEE Access.

[16]  Nishtha Hooda,et al.  Big Data Deep Learning Framework using Keras: A Case Study of Pneumonia Prediction , 2018, 2018 4th International Conference on Computing Communication and Automation (ICCCA).

[17]  Ghufran Ahmed,et al.  Deep Learning based Ensemble Convolutional Neural Network Solution for Distributed Denial of Service Detection in SDNs , 2019, 2019 UK/ China Emerging Technologies (UCET).

[18]  Keshav P. Dahal,et al.  Suspicious Traffic Detection in SDN with Collaborative Techniques of Snort and Deep Neural Networks , 2018, 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS).

[19]  Joel J. P. C. Rodrigues,et al.  Hybrid Deep-Learning-Based Anomaly Detection Scheme for Suspicious Flow Detection in SDN: A Social Multimedia Perspective , 2019, IEEE Transactions on Multimedia.

[20]  Yang Xiang,et al.  A novel organizing scheme of single topic user group based on trust chain model in social network , 2018, Int. J. Commun. Syst..

[21]  Sharifah Hafizah Syed Ariffin,et al.  A Review of Anomaly Detection Techniques and Distributed Denial of Service (DDoS) on Software Defined Network (SDN) , 2018 .

[22]  Sung Won Kim,et al.  Hybrid Deep Learning: An Efficient Reconnaissance and Surveillance Detection Mechanism in SDN , 2020, IEEE Access.