Intrusion detection for MANET to detect unknown attacks using Genetic algorithm

Lalli, M.; Palanisamy, V.

doi:10.1109/iccic.2014.7238505

Cited by 3 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Game Theory can also be used for trust management between the nodes participating in detection of threats in the system. Genetic Algorithms have a better detection rate as shown in [36,37,38] than Evolution Strategies [35] although both technologies follow a similar apporach. GA algorithms are behaving effectively, from resources allocation and execution time [18], for feature reduction.…”

Section: Discussionmentioning

confidence: 99%

“…This indicates that the Evolutionary approach GA follows is effective against detecting different types of attacks as well as different variations of the same attack. Also, GA is able to detect other types of (D)DoS attacks such as Grayhole and packet GT [32] (D)DoS Attacks Prevention GT [33] (D)DoS Attacks Prevention EA [34] SIP Flooding Attacks 82.17% and 77.00% ES [35] Darpa (D)DoS attacks No Results GA [36] Blackhl. & Packt.…”

Section: Discussionmentioning

confidence: 99%

“…The authors in [36] designed an IDS for MANETs using GA to detect black hole and dropping routing DoS attacks. They defined a set of characteristics for the GA algorithm to consider (whether connections was from/to similar port/host, number of wrong fragments within the connection, connection SYN errors, percentage of connections to similar/desimilar services and hosts and so on).…”

Section: Genetic Algorithms 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: Discussionmentioning

confidence: 99%