An Adaptive Protection of Flooding Attacks Model for Complex Network Environments. (23rd April 2021)

• Record Type: Journal Article
• Authors: Khalaf, Bashar Ahmad; Mostafa, Salama A.; Mustapha, Aida; Mohammed, Mazin Abed; Mahmoud, Moamin A.; Al-Rimy, Bander Ali Saleh; Abd Razak, Shukor; Elhoseny, Mohamed; Marks, Adam
• Other Names: Vorakulpipat Chalee Academic Editor.
• Is Part Of: Security and communication networks. Volume 2021(2021)
• Publication Date: 2021-04-23
• Subjects: Computer networks -- Security measures -- Periodicals; Computer security -- Periodicals; Cryptography -- Periodicals; 005.805
• DOI: 10.1155/2021/5542919
• Languages: English
• ISSNs: 1939-0114

Abstract

Abstract : Currently, online organizational resources and assets are potential targets of several types of attack, the most common being flooding attacks. We consider the Distributed Denial of Service (DDoS) as the most dangerous type of flooding attack that could target those resources. The DDoS attack consumes network available resources such as bandwidth, processing power, and memory, thereby limiting or withholding accessibility to users. The Flash Crowd (FC) is quite similar to the DDoS attack whereby many legitimate users concurrently access a particular service, the number of which results in the denial of service. Researchers have proposed many different models to eliminate the risk of DDoS attacks, but only few efforts have been made to differentiate it from FC flooding as FC flooding also causes the denial of service and usually misleads the detection of the DDoS attacks. In this paper, an adaptive agent-based model, known as an Adaptive Protection of Flooding Attacks (APFA) model, is proposed to protect the Network Application Layer (NAL) against DDoS flooding attacks and FC flooding traffics. The APFA model, with the aid of an adaptive analyst agent, distinguishes between DDoS and FC abnormal traffics. It then separates DDoS botnet from Demons and Zombies to apply suitable attack handling methodology. There are three parameters on which the agent relies, normal traffic intensity, traffic attack behavior, and IP address history log, to decide on the operation of two traffic filters. We test and evaluate the APFA model via a simulation system using CIDDS as a standard dataset. The model successfully adapts to the simulated attack scenarios' changes and determines 303, 024 request conditions for the tested 135, 583 IP addresses. It achieves an accuracy of 0.9964, a precision of 0.9962, and a sensitivity of 0.9996, and outperforms three tested similar models. In addition, the APFA model contributes to identifying and handling the actual trigger of DDoS attack and differentiates it from FC flooding, which is rarely implemented in one model.