The Effect of Dimensionality Reduction on Software Vulnerability Prediction Models

Stuckman, Jeffrey; Walden, James; Scandariato, Riccardo

doi:10.1109/tr.2016.2630503

Cited by 50 publications

(52 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The features are the appearance frequency of the tokens, i.e., unigrams, in the code of the components. As the features dimensionality explodes quickly reducing it is mandatory [35,40]. To this end, previous studies [35,40] discretized the frequency of tokens (to make them binary) using the method of Kononenko [24].…”

Section: Bag Of Wordsmentioning

confidence: 99%

The importance of accounting for real-world labelling when predicting software vulnerabilities

Jiménez

Rwemalika

Papadakis

et al. 2019

Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of

View full text Add to dashboard Cite

Previous work on vulnerability prediction assume that predictive models are trained with respect to perfect labelling information (includes labels from future, as yet undiscovered vulnerabilities). In this paper we present results from a comprehensive empirical study of 1,898 real-world vulnerabilities reported in 74 releases of three security-critical open source systems (Linux Kernel, OpenSSL and Wiresark). Our study investigates the effectiveness of three previously proposed vulnerability prediction approaches, in two settings: with and without the unrealistic labelling assumption. The results reveal that the unrealistic labelling assumption can profoundly mislead the scientific conclusions drawn; suggesting highly effective and deployable prediction results vanish when we fully account for realistically available labelling in the experimental methodology. More precisely, MCC mean values of predictive effectiveness drop from 0.77, 0.65 and 0.43 to 0.08, 0.22, 0.10 for Linux Kernel, OpenSSL and Wiresark, respectively. Similar results are also obtained for precision, recall and other assessments of predictive efficacy. The community therefore needs to upgrade experimental and empirical methodology for vulnerability prediction evaluation and development to ensure robust and actionable scientific findings. CCS CONCEPTS • Software and its engineering → Software defect analysis.

show abstract

Section: Bag Of Wordsmentioning

confidence: 99%

The importance of accounting for real-world labelling when predicting software vulnerabilities

Jiménez

Rwemalika

Papadakis

et al. 2019

Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of

View full text Add to dashboard Cite

show abstract

“…The classification algorithm is also used for detection of software fault and software vulnerability. Jeffrey Stuckman et al investigated the effect of dimensionality reduction in predicting the software vulnerability [5]. Furthermore, some of the researchers concentrated on improving the accuracy in recognition and clustering tasks using dimensionality reduction.…”

Section: Related Workmentioning

confidence: 99%

Dimensionality Reduction for Classification and Clustering

Singh¹,

Leavline²

2019

IJISA

View full text Add to dashboard Cite

Now-a-days, data are generated massively from various sectors such as medical, educational, commercial, etc. Processing these data is a challenging task since the massive data take more time to process and make decision. Therefore, reducing the size of data for processing is a pressing need. The size of the data can be reduced using dimensionality reduction methods. The dimensionality reduction is known as feature selection or variable selection. The dimensionality reduction reduces the number of features present in the dataset by removing the irrelevant and redundant variables to improve the accuracy of the classification and clustering tasks. The classification and clustering techniques play a significant role in decision making. Improving accuracy of classification and clustering is an essential task of the researchers to improve the quality of decision making. Therefore, this paper presents a dimensionality reduction method with wrapper approach to improve the accuracy of classification and clustering. Index Terms-Wrapper-based dimensionality reduction, naï ve Bayes classifier, Random forest classifier, OneR classifier, Variable selection. Resource Management, and Ph. D in Information and Communication Engineering degrees from Anna University, India. He is currently working as a teaching fellow in the Department of Computer Science and Engineering, Anna University, BIT-Campus, Tiruchirappalli, India. His research interests include data mining, wireless networks, parallel computing, mobile computing, computer networks, image processing, software engineering, soft computing, cloud computing, big data analytics, teaching learning process and engineering education, human resource management.

show abstract

“…e results indicate that the values of vulnerability densities fall within a range of values and reveals that it is possible to model the vulnerability discovery using a logistic model that can sometimes be approximated by a linear model. Jeffrey et al [13] compared models based on the software metrics and term frequencies and explored the role of dimensionality reduction through a series of crossvalidation and crossproject prediction experiments. e results showed that, in the case of software metrics, a dimensionality reduction technique based on confirmatory factor analysis provided an advantage when performing crossproject prediction, yielding the best F-measure for the predictions in five out of six cases.…”

Section: Introductionmentioning

confidence: 99%

Study on Software Vulnerability Characteristics and Its Identification Method

Luo

Wang

Huang

et al. 2020

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A method for identifying software data flow vulnerabilities is proposed based on the dendritic cell algorithm and the improved convolutional neural network to effectively solve the transmission errors in software data flow. In this method, we first gave the software data flow propagation model and constructed the data propagation tree structure. Secondly, we analyzed the running characteristics of the software, took the interaction among indexes into account, and identified data flow vulnerabilities using the dendritic cell algorithm and the improved convolutional neural network. Finally, we conducted an in-depth study on the performance of this method and other algorithms through mathematical simulation. The results show that this method has better advantages in detection time, storage cost, and software code size.

show abstract

The Effect of Dimensionality Reduction on Software Vulnerability Prediction Models

Cited by 50 publications

References 46 publications

The importance of accounting for real-world labelling when predicting software vulnerabilities

The importance of accounting for real-world labelling when predicting software vulnerabilities

Dimensionality Reduction for Classification and Clustering

Study on Software Vulnerability Characteristics and Its Identification Method

Contact Info

Product

Resources

About