Composing Signatures for Misuse Intrusion Detection System Using Genetic Algorithm in an Offline Environment

Goyal, Mayank Kumar; Aggarwal, Alok

doi:10.1007/978-3-642-31513-8_16

Cited by 23 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The nodes use a dendrite cell algorithm to detect the intruder. In [2] a genetic algorithm based approach which uses a set of classification rules is presented. The classical rules are generated from a predefined network intrusion behavior.…”

Section: Related Workmentioning

confidence: 99%

D0m-Wlan

Nanda

Krishna

2013

Proceedings of the 6th International Conference on Security of Information and Networks

View full text Add to dashboard Cite

The recent research in the wireless network technologies focuses on numerous security threats in a network. Users tend to keep their systems virus free but don't give much focus to online security. The recent trends in intrusion detection have suggested that most of the malicious and abnormal activities can be identified by capturing the network traffic and analyzing them. Many research works in this area address only a particular problem focusing on a network attack or a behavioral pattern of certain kind of worms and Trojans, and propose a solution for that. This gives solution to only a particular type of intrusion detection and leaves the remaining problems apart. There is a need for a kind of system which can handle different types of malicious activities on the wireless local area network. We have developed a traffic analysis tool which focuses on detection of network attacks, fixed signatures, behavioral methods and suspicious packets. Our tool addresses different intrusions pertaining to different detection methods.Its implementation for both LAN and Wireless LAN showed good results on MIT Lincoln DARPA Dataset and also on real time traffic. The scalability of the tool showed it is highly efficient and can be deployed for real time use.

show abstract

Section: Related Workmentioning

confidence: 99%

D0m-Wlan

Nanda

Krishna

2013

Proceedings of the 6th International Conference on Security of Information and Networks

View full text Add to dashboard Cite

show abstract

“…A probabilistic classifier detects anomalies and a hidden Markov model narrows down attacker addresses [13]. Recently, genetic algorithms have been widely used in anomaly detection and misuse detection [14], [15]. Another recent development is using artificial immune systems (AIS) in intrusion detection [16].…”

Section: Related Researchmentioning

confidence: 99%

An Efficient Network Log Anomaly Detection System Using Random Projection Dimensionality Reduction

Juvonen

Hämäläinen

2014

2014 6th International Conference on New Technologies, Mobility and Security (NTMS)

View full text Add to dashboard Cite

Abstract-Network traffic is increasing all the time and network services are becoming more complex and vulnerable. To protect these networks, intrusion detection systems are used. Signature-based intrusion detection cannot find previously unknown attacks, which is why anomaly detection is needed. However, many new systems are slow and complicated. We propose a log anomaly detection framework which aims to facilitate quick anomaly detection and also provide visualizations of the network traffic structure. The system preprocesses network logs into a numerical data matrix, reduces the dimensionality of this matrix using random projection and uses Mahalanobis distance to find outliers and calculate an anomaly score for each data point. Log lines that are too different are flagged as anomalies. The system is tested with real-world network data, and actual intrusion attempts are found. In addition, visualizations are created to represent the structure of the network data. We also perform computational time evaluation to ensure the performance is feasible. The system is fast, finds real intrusion attempts and does not need clean training data.

show abstract

“…A probabilistic classifier detects anomalies and a hidden Markov model narrows down attacker addresses [8]. Recently genetic algorithms have been widely used in anomaly detection and misuse detection [9], [10]. Artificial immune systems have raised the interest of intrusion detection researchers [11].…”

Section: Anomaly-based Intrusion Detection Systemmentioning

confidence: 99%