Biologically-inspired Complex Adaptive Systems approaches to Network Intrusion Detection

Shafi, Kamran; Abbass, Hussein A.

doi:10.1016/j.istr.2007.09.001

Cited by 26 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main strength is that they are parallel in nature [17] GAs and PSO are commonly associated with the optimization of continuous numerical functions, and ACO with combinatorial optimization [16]. Some of the benefits of adopting such techniques are flexibility in retraining, online/continuous learning and the potential for parallelism in the algorithms, which can be exploited both in the training and detection process.…”

Section: Swarm Intelligence In Intrusion Detectionmentioning

confidence: 99%

Data Preprocessing for Intrusion Detection System using Swarm Intelligence Techniques

Revathi¹,

Malathi²

2013

IJCA

View full text Add to dashboard Cite

Due to access of malicious data in internet, Intrusion detection system becomes an important element in system security that controls real time data and leads to huge dimensional problem, so a data pre-processing is necessary to reduce haziness and to clean network data. To reduce false positive rate and to increase efficiency of detection, the paper proposed a new swarm intelligence technique to solve complex optimization problem. The paper work based on hybrid Simplified Swarm Optimization (SSO) algorithm to pre-process the data. SSO is a simplified Particle Swarm Optimization (PSO) that has a self-organizing ability to emerge in highly distributed control problem area, and is versatile, strong and cost effective to resolve complex computing environments. It recognize not only known attacks but also filters noisy and irrelevant data that may result on knowledge Discovery and Data Mining (KDDCup 1999) dataset and compared to a new hybrid Partial Swarm Optimization with Random Forest (PSO-RF) and with other benchmark classifiers. The testing result shows that the proposed method provides competitively high detection rates and produce a near optimal solution.

show abstract

Section: Swarm Intelligence In Intrusion Detectionmentioning

confidence: 99%

Data Preprocessing for Intrusion Detection System using Swarm Intelligence Techniques

Revathi¹,

Malathi²

2013

IJCA

View full text Add to dashboard Cite

show abstract

“…The Internet Sensor Grid would be a CAS in itself as they would be collaborative systems of many components that detect, share, initiate protection or launch countermeasures [22]. Such a system may be based on biologically inspired immune system concepts [23], virally spreading the key information to enable reaction and countermeasures [24] like an immune system using antibodies [25]. Existing work on collective intelligence [26] may also be incorporated but needs to be evaluated to fit with this problem space.…”

Section: The Internet Sensor Gridmentioning

confidence: 99%

“…Existing work on collective intelligence [26] may also be incorporated but needs to be evaluated to fit with this problem space. Key areas to be developed cover the creation of collaborative sensors and actuators [25,17,28,29], detection and classification of emergent behaviour [3,4], inventing and testing system response and counter-measures. Current basic systems are proving successful, e.g.…”

Section: The Internet Sensor Gridmentioning

confidence: 99%

Internet Sensor Grid: Experiences with Passive and Active Instruments

Komisarczuk

Welch

2010

Communications: Wireless in Developing Countries and Networks of the Future

View full text Add to dashboard Cite

Abstract. The Internet is constantly evolving with new emergent behaviours arising; some of them malicious. This paper discusses opportunities and research direction in an Internet sensor grid for malicious behaviour detection, analysis and countermeasures. We use two example sensors as a basis; firstly the honeyclient for malicious server and content identification (i.e. drive-bydownloads, the most prevalent attack vector for client systems) and secondly the network telescope for Internet Background Radiation detection (IBRwhich is classified as unsolicited, non-productive traffic that traverses the Internet, often malicious in nature or origin). Large amounts of security data can be collected from such sensors for analysis and federating honeyclient and telescope data provides a worldwide picture of attacks that could enable the provision of countermeasures. In this paper we outline some experiences with these sensors and analyzing network telescope data through Grid computing as part of an "intelligence layer" within the Internet.

show abstract

“…Goel and Bush [19] propose a system that is able to create new virus -signatures by mutation of the existing signatures. Shafi and Abbass [40] present in their work a more holistic approach as they consider several Complex Adaptive Systems with foundations in the physical world. They examine paradigms of security systems that utilize Genetics Based Machine Learning, Swarm Intelligence and Coevolution.…”

Section: Related Workmentioning

confidence: 99%

Biological Aspects of Computer Virology

Vlachos

Spinellis

Androutsellis-Theotokis

2010

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Abstract. Recent malware epidemics proved beyond any doubt that frightful predictions of fast-spreading worms have been well founded. While we can identify and neutralize many types of malicious code, often we are not able to do that in a timely enough manner to suppress its uncontrolled propagation. In this paper we discuss the decisive factors that affect the propagation of a worm and evaluate their effectiveness.

show abstract

Biologically-inspired Complex Adaptive Systems approaches to Network Intrusion Detection

Cited by 26 publications

References 40 publications

Data Preprocessing for Intrusion Detection System using Swarm Intelligence Techniques

Data Preprocessing for Intrusion Detection System using Swarm Intelligence Techniques

Internet Sensor Grid: Experiences with Passive and Active Instruments

Biological Aspects of Computer Virology

Contact Info

Product

Resources

About