English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Vulnerability prediction refers to the problem of identifying systemcomponents that are most likely to be vulnerable. Typically, this problem istackled by training binary classifiers on historical data. Unfortunately,recent research has shown that such approaches underperform due to thefollowing two reasons: a) the imbalanced nature of the problem, and b) theinherently noisy historical data, i.e., most vulnerabilities are discoveredmuch later than they are introduced. This misleads classifiers as they learn torecognize actual vulnerable components as non-vulnerable. To tackle theseissues, we propose TROVON, a technique that learns from known vulnerablecomponents rather than from vulnerable and non-vulnerable components, astypically performed. We perform this by contrasting the known vulnerable, andtheir respective fixed components. This way, TROVON manages to learn from thethings we know, i.e., vulnerabilities, hence reducing the effects of noisy andunbalanced data. We evaluate TROVON by comparing it with existing techniques onthree security-critical open source systems, i.e., Linux Kernel, OpenSSL, andWireshark, with historical vulnerabilities that have been reported in theNational Vulnerability Database (NVD). Our evaluation demonstrates that theprediction capability of TROVON significantly outperforms existingvulnerability prediction techniques such as Software Metrics, Imports, FunctionCalls, Text Mining, Devign, LSTM, and LSTM-RF with an improvement of 40.84% inMatthews Correlation Coefficient (MCC) score under Clean Training DataSettings, and an improvement of 35.52% under Realistic Training Data Settings.

Learning from What We Know: How to Perform Vulnerability Prediction using Noisy Historical Data