The Danger Theory and its Application to Artificial Immune Systems

Aickelin, Uwe; Cayzer, Steve

doi:10.2139/ssrn.2832054

Cited by 146 publications

(128 citation statements)

References 16 publications

(24 reference statements)

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…The use of a danger signal in AIS research was popularized by Aickelin and Cayzer [62], despite a mention in Hofmeyr and Forrest's LISYS work two years earlier [58], and Burgess' notice of it two years prior still [63]. The usefulness of the danger signal concept in AIS is that suspicious activities, such as a spike in network traffic, can be used to influence the artificial immune response.…”

Section: Danger Signalsmentioning

confidence: 99%

See 1 more Smart Citation

A taxonomy of biologically inspired research in computer networking

2010

View full text Add to dashboard Cite

a b s t r a c tThe natural world is enormous, dynamic, incredibly diverse, and highly complex. Despite the inherent challenges of surviving in such a world, biological organisms evolve, self-organize, self-repair, navigate, and flourish. Generally, they do so with only local knowledge and without any centralized control. Our computer networks are increasingly facing similar challenges as they grow larger in size, but are yet to be able to achieve the same level of robustness and adaptability. Many research efforts have recognized these parallels, and wondered if there are some lessons to be learned from biological systems. As a result, biologically inspired research in computer networking is a quickly growing field. This article begins by exploring why biology and computer network research are such a natural match. We then present a broad overview of biologically inspired research, grouped by topic, and classified in two ways: by the biological field that inspired each topic, and by the area of networking in which the topic lies. In each case, we elucidate how biological concepts have been most successfully applied. In aggregate, we conclude that research efforts are most successful when they separate biological design from biological implementation -that is to say, when they extract the pertinent principles from the former without imposing the limitations of the latter.

show abstract

Section: Danger Signalsmentioning

confidence: 99%

“…According to their evaluation, the danger signal greatly reduced the number of false positives [64]. However, the majority of publications on the use of the danger theory in AIS have been produced by its most outspoken proponents, Aickelin et al [62,65,66].…”

Section: Danger Signalsmentioning

confidence: 99%

A taxonomy of biologically inspired research in computer networking

2010

View full text Add to dashboard Cite

show abstract

“…The number and strength of DC cytokine output depends on its current maturation state. The proposal presented by Aickelin and Cayzer [7] to DT model has encouraged many AIS, mainly computer security developers, to discover the potentials of danger theory [8,9,10]. Our system uses the danger theory as forcefulness concept for inspiration to intrusion detection system integrated with adaptive immune system mechanisms, mainly DC as classifier, T-cell and B-cell mechanisms.…”

Section: Human Immun Systemmentioning

confidence: 99%

Immune Multiagent System for Network Intrusion Detection using Non-linear Classification Algorithm

Mohamed¹,

Samir

Abdullah

2010

IJCA

View full text Add to dashboard Cite

The growth of intelligent intrusion and diverse attack techniques in network systems stimulate computer scientists and mathematical researchers to challenge the dangers of intelligent attacks. In this work, we integrate artificial immune algorithm with non-linear classification of pattern recognition and machine learning methods to solve the problem of intrusion detection in network systems. A new non classification algorithm was developed based on the danger theory model of human immune system (HIS).The abstract model of system algorithm is inspired from HIS cell mechanism mainly, the Dendritic cell behavior and T-cell mechanisms. Classification techniques using k-nearest neighbor (k-NN) or Gaussian Mixture (GMM) almost have the common sense that they believe the neighboring data. The algorithm tested use KDD Cup dataset and the result shows a significant improvement in detection accuracy and reducing the false alerts.

show abstract

“…It is thought that danger signals, such as those exposed to pathogens, toxins, mechanical damage, and so forth, are detected and processed through professional APCs. The danger model is presented in [5] and the applications of danger model to AIS were identified and discussed in depth in [12].…”

Section: Self Versus Non-selfmentioning

confidence: 99%

Conserved Self Pattern Recognition Algorithm

Dasgupta

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Self-nonself model makes a lot of sense in the mechanisms of self versus nonself recognition in the immune system but it failed to explain a great number of findings. Some new immune theory is proposed to accommodate incompatible new findings, including Pattern Recognition Receptors (PRRs) Model and Danger Theory. Inspired from the PRRs model, a novel approach called Conserved Self Pattern Recognition Algorithm (CSPRA) is proposed in this paper. The algorithm is tested using the famous benchmark Fisher's Iris data. Preliminary results demonstrate that the new approach lowers the false positive and thus enhances the efficiency and reliability for anomaly detection without increase in complexity comparing to the classical Negative Selection Algorithm (NSA).

show abstract

The Danger Theory and its Application to Artificial Immune Systems

Cited by 146 publications

References 16 publications

A taxonomy of biologically inspired research in computer networking

A taxonomy of biologically inspired research in computer networking

Immune Multiagent System for Network Intrusion Detection using Non-linear Classification Algorithm

Conserved Self Pattern Recognition Algorithm

Contact Info

Product

Resources

About