Poster: Understanding The Hidden Cost Of Software Vulnerabilities: Measurements And Predictions
Keywords
NVD; Prediction; Vulnerability Economics
Abstract
In this work, we study the hidden cost of software vulnerabilities reported in the National Vulnerability Database (NVD) through stock price analysis. We perform a high-fidelity data augmentation to ensure data reliability for estimating vulnerability disclosure dates as a baseline for assessing software vulnerabilities' implication. We further build a model for stock price prediction using the NARX Neural Network model to estimate the effect of vulnerability disclosure on the stock price. Compared to prior work, which relies on linear regression models, our approach is shown to provide better accuracy. Our analysis shows that the effect of vulnerabilities on vendors varies, and greatly depends on the specific industry.
Publication Date
5-29-2018
Publication Title
ASIACCS 2018 - Proceedings of the 2018 ACM Asia Conference on Computer and Communications Security
Number of Pages
793-795
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1145/3196494.3201580
Copyright Status
Unknown
Socpus ID
85049155661 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85049155661
STARS Citation
Anwar, Afsah; Khormali, Aminollah; and Mohaisen, Aziz, "Poster: Understanding The Hidden Cost Of Software Vulnerabilities: Measurements And Predictions" (2018). Scopus Export 2015-2019. 10554.
https://stars.library.ucf.edu/scopus2015/10554