Abstract | ||
---|---|---|
The increasing number of malware in the past 4 years has determined researchers to test different machine learning techniques to automate the detection system. But because of the large size of the dataset and the need of having a high detection rate, the resulted models have often produced many false positives. This paper proposes a modified version of the perceptron algorithm able to detect malware samples while training at a low rate (even zero) of false positives. A very low number of false positives is crucial because in a real life situation detecting a clean file as malware can destroy the operating system or render other programs unusable. We also provide a method of optimizing the training speed for the algorithm while maintaining the same accuracy. The resulted algorithm can be used in an ensemble or voting system to increase detection and eliminate false positives. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/SYNASC.2012.34 | Symbolic and Numeric Algorithms for Scientific Computing |
Keywords | Field | DocType |
increasing number,detection system,operating system,optimized zero false positives,low rate,training speed,low number,high detection rate,voting system,false positive,perceptron training,malware detection,malware sample,data mining,distributed algorithms,learning artificial intelligence | Data mining,Voting,Computer science,Theoretical computer science,Distributed algorithm,Artificial intelligence,Malware,Perceptron,Machine learning,False positive paradox | Conference |
ISSN | ISBN | Citations |
2470-8801 | 978-1-4673-5026-6 | 15 |
PageRank | References | Authors |
1.36 | 9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dragos Gavrilut | 1 | 62 | 7.95 |
Razvan Benchea | 2 | 26 | 3.76 |
Cristina Vatamanu | 3 | 31 | 3.61 |