Immunocomputing for intelligent intrusion detection

Tarakanov, Alexander O.

doi:10.1109/mci.2008.919069

Cited by 26 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These advances of the IC approach together with its biologic nature probably mean a further step toward placing on the chip more of the functions of intelligent signal processing [34,45]. For example, this chip could be selfadapted to different types of signals (e.g., audio, video, sonar, radar, etc.)…”

Section: Resultsmentioning

confidence: 99%

“…For example, an enhanced SVM for intrusion detection in [44] needs at least four steps to adopt KDD data [39]: (1) consider only binary classification, (2) filter the ''redundant'' intrusion records, (3) perform feature ranking and (4) delete the ''unimportant'' features. Note that FIN is free of similar steps and is applied directly to the same KDD data [45].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Immunocomputing for intelligent signal processing

Tarakanov

2010

Neural Comput & Applic

View full text Add to dashboard Cite

Based on immunocomputing (IC), this paper describes an approach to intelligent signal processing. The approach includes both low-level feature extraction and high-level (intelligent) pattern recognition. The key model is the formal immune network (FIN), which includes apoptosis (programmed cell death) and immunization and controls them by cytokines (messenger proteins). Such FIN can be formed from the signal or combination of signals using discrete tree transform, singular value decomposition and the proposed index of inseparability as a measure of quality of FIN. Several comparisons with neural computing and support vector machines suggest that IC may outperform state of the art approaches to intelligent signal processing.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Immunocomputing for intelligent signal processing

Tarakanov

2010

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…FIN proposes the generation of a Euclidean multidimensional space (FIN space) in which a training process based on application of a discrete tree transform (DTT) [1] and/or a singular value descomposition (SVD) [13] incorporates input data and its initial space, which is optimized to form a set of class representatives for representation called cytokines, following a process of apoptosis and immunization explained in [24]. These cytokines operate according to a proximity principle in the FIN space to determine the class of data reviewed when mapped in the space with the DTT algorithm.…”

Section: -Formal Immune Network (Fin)mentioning

confidence: 99%

“…It is precisely this difference of concepts that has given rise to a prolific and diverse set [4] of hybrid techniques collectively called Artificial Immune Systems [10]. All these proposals seek to rescue capacities of identification, threat elimination, failure tolerance and adaptability of Biological Immune Systems through a series of proposals such as Formal Immune Network (FIN) [24], which is based on programmed cell death and cytokine-controlled immunization (messenger proteins), Clonal Selection (CLONALG), which posits a proliferation of detectors capable of detecting antigens and exploring them in order to enhance affinity by means of somatic hypermutation [5], Negative Selection (LISYS) [9] which is based on the maturation of T lymphocytes to produce immunological tolerance [12] and models based on the Jerne immune network [3]. There is evidence that these techniques do not deal with the change of normality in a consistent manner, while they also rely on models that are partial and not fully accepted [28].…”

Section: Introductionmentioning

confidence: 99%

An Ecological Approach to Anomaly Detection: The EIA Model

Pinacho

Pau

Chacón

et al. 2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The presented work proposes a new approach for anomaly detection. This approach is based on changes in a population of evolving agents under stress. If conditions are appropriate, changes in the population (modeled by the bioindicators) are representative of the alterations to the environment. This approach, based on an ecological view, improves functionally traditional approaches to the detection of anomalies.To verify this assertion, experiments based on Network Intrussion Detection Systems are presented. The results are compared with the behaviour of other bioinspired approaches and machine learning techniques.

show abstract

“…В последнее время появилось много работ, посвященных искусствен-ным иммунным системам. Искусственные иммунные системы (AISsArtificial immune systems) [65,71] и иммуннокомпьютинг (ICImmunocomputing) [130,131,142] часто воспринимаются исследовате-лями как интерпретация генетических алгоритмов [133] и искусствен-ных нейронных сетей (ANNs -Artificial neural networks), которые также называют нейрокомпьютингом [132].…”

unclassified

Untitled

Нестерук¹,

Kotenko²,

Шоров³

2019

Тр. СПИИРАН

View full text Add to dashboard Cite

И.В., Шоров А.В., Нестерук Ф.Г. Анализ биоинспирированных подходов для защиты компьютерных систем и сетей. Аннотация. В настоящее время в области безопасности компьютерных систем и сетей все чаще упоминаются и рекламируются различные биоинспирированные подходы, то есть подходы, основанные на биологической метафоре. Действительно, традиционные компьютерные методы и системы, как правило, ограничены по своим функциональным возможностям, подвержены частому выходу из строя из-за незначительных ошибок, имеют недостаточную масштабируемость, не обладают способностью к адаптации к условиям функционирования и изменению целей. В противоположность этому, биоло-гические системы, как правило, реализуют развитые механизмы самозащиты, достаточ-но надежны, обладают высокой масштабируемостью, адаптивны и способны к саморе-генерации. Указанные свойства биологических систем стимулируют использование принципов их построения и механизмов их функционирования в технических системах, включая системы защиты информации. В данной статье рассматриваются различные подходы к защите компьютерных систем и сетей, в основе которых лежит биологиче-ская метафора. Ключевые слова: биологическая метафора, защита компьютерных систем и сетей, им-мунокомпьютинг, нейронные сети, гибридные интеллектуальные средства.Kotenko I.V., Shorov A.V., Nesteruk P.G. Analysis of bio-inspired approaches for protection of computer systems and networks. Abstract. Nowadays more and more different bio-inspired approaches (based on a biological metaphor) for the computer and networks security systems are mentioned and advertised. Traditional computer-based systems and their functionality are often limited by different conditions. Due to frequent minor errors, these systems are subject of failure. They lack scalability, have low adaptation ability to changeable conditions of functioning and its goals. As opposed to traditional computer-based systems, biological systems are often quite reliable. They have great self-protection mechanisms, highly scalable, adaptable and able to self regeneration. These properties of biological systems can be used to construct technical systems (including information security systems). The paper considers different approaches to the protection of computer systems and networks, which are based on a biological metaphor.

show abstract

Immunocomputing for intelligent intrusion detection

Cited by 26 publications

References 21 publications

Immunocomputing for intelligent signal processing

Immunocomputing for intelligent signal processing

An Ecological Approach to Anomaly Detection: The EIA Model

Untitled

Contact Info

Product

Resources

About