Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation 2006
DOI: 10.1145/1143997.1144016
|View full text |Cite
|
Sign up to set email alerts
|

A retrovirus inspired algorithm for virus detection & optimization

Abstract: In the search for a robust and efficient algorithm to be used for computer virus detection, we have developed an artificial immune system genetic algorithm (REALGO) based on the human immune system's use of reverse transcription ribonucleic acid (RNA). The REALGO algorithm provides memory such that during a complex search the algorithm can revert back to and attempt to mutate in a different "direction" in order to escape local minima. In lieu of non-existing virus generic templates, validation is addressed by … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
9
0

Year Published

2007
2007
2020
2020

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 22 publications
(9 citation statements)
references
References 17 publications
0
9
0
Order By: Relevance
“…The signature generator uses signatures which are defined as the string patterns which are unique to identify and characterize the malware. In another work proposed by Edge et al [15], an artificial immune system genetic algorithm (REALGO) was developed based on the human immune system's use of reverse transcription ribonucleic acid (RNA). The REALGO algorithm combines known information from past viruses with a type of prediction for future viruses.…”
Section: Evolutionary Approaches For Pattern Generationmentioning
confidence: 99%
“…The signature generator uses signatures which are defined as the string patterns which are unique to identify and characterize the malware. In another work proposed by Edge et al [15], an artificial immune system genetic algorithm (REALGO) was developed based on the human immune system's use of reverse transcription ribonucleic acid (RNA). The REALGO algorithm combines known information from past viruses with a type of prediction for future viruses.…”
Section: Evolutionary Approaches For Pattern Generationmentioning
confidence: 99%
“…Forrest et al first proposed an NSA to detect abnormal modification on protected data [1] and later applied it to UNIX process detection [8]. Since then, more and more researchers have devoted themselves to the study of computer immune systems based on immune mechanisms and many immune based computer malware detection models have been proposed [9][10][11][12][13].…”
Section: Related Workmentioning
confidence: 99%
“…In addition, we pursue a multiobjective approach because the consolidation of information into a single aggregated objective tends to lose data granularity and offer the decisionmaker only one solution vice a set of trade-off solutions. The solution approach develops a new proof-of-concept algorithm that advances the existing work of two AIS-motivated algorithms: Edge, Lamont and Raines' retrovirus algorithm (REALGO) [6] for its ability to escape local optima, with regard to string matching, and Coello and Cortés' multiobjective immune system algorithm (MISA) [5] for its employment of an AIS in a multiobjective EA context.…”
Section: Hypothesismentioning
confidence: 99%
“…The C-to-Java migration experiment is straightforward, yet we are concerned about the impact of a different programming language and random number generator on the output. Figure 6 compares the output between REALGO and jREALGO, employing REALGO's Yao and Liu's test function [6]where the optimal value is -12569.5. Figure 7 compares the output between MISA and jMISA, employing MISA's Kita-proposed two-variable test function [5].…”
Section: Experimentation and Analysismentioning
confidence: 99%