USP Electronic Research Repository

Ransomware noise identification and eviction through machine learning fundamental filters

Sharma, Priynka and Chaudhary, Kaylash C. and Khan, Mohammad G.M. and Wagner, Michael (2020) Ransomware noise identification and eviction through machine learning fundamental filters. [Conference Proceedings]

Full text not available from this repository.


The existence of noise in a Ransomware dataset can negatively affect the classification model constructed. More explicitly, the noisy examples in the dataset can antagonistically influence the learnt hypothesis. Eviction of noisy occurrences will improve the hypothesis; thus, improving the classification precision of the model. This paper acquaints a novel strategy through upgraded inferiority of training ransomware data with a noisy dependent variable for multiclass classification problems. Noise diminishes classification accuracy by disturbing the informational training index and setting off the classifier to assemble erroneous models. Our methodology uses a Machine Learning Fundamental Filters (MLFF) to arrange suspicious noisy examples and prototype selection (PS) in order to recognise the set of real noisy occurrences in ransomware dataset. This paper shows that the tuning of MLFF with prototype selection improves the nature of noisy training data collections; thus, increases the classification precision of the model trained with the training dataset without noise.

Item Type: Conference Proceedings
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User: Ms Shalni Sanjana
Date Deposited: 13 Aug 2020 04:19
Last Modified: 03 Dec 2020 21:16

Actions (login required)

View Item View Item