| Title | Early Detection of Vulnerabilities from News Websites using Machine Learning Models |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Iorga, Denis, Corlătescu, Dragos, Grigorescu, Octavian, Săndescu, Cristian, Dascălu, Mihai, Rughiniş, Razvan |
| Conference Name | 2020 19th RoEduNet Conference: Networking in Education and Research (RoEduNet) |
| Date Published | dec |
| Keywords | BERT language model, Bit error rate, compositionality, computer security, cybernetics, data mining, Data models, early detection, Human Behavior, Metrics, natural language processing, OSINT, pubcrawl, Resiliency, Support vector machines, Task Analysis, vulnerability detection |
| Abstract | The drawbacks of traditional methods of cybernetic vulnerability detection relate to the required time to identify new threats, to register them in the Common Vulnerabilities and Exposures (CVE) records, and to score them with the Common Vulnerabilities Scoring System (CVSS). These problems can be mitigated by early vulnerability detection systems relying on social media and open-source data. This paper presents a model that aims to identify emerging cybernetic vulnerabilities in cybersecurity news articles, as part of a system for automatic detection of early cybernetic threats using Open Source Intelligence (OSINT). Three machine learning models were trained on a novel dataset of 1000 labeled news articles to create a strong baseline for classifying cybersecurity articles as relevant (i.e., introducing new security threats), or irrelevant: Support Vector Machines, a Multinomial Naive Bayes classifier, and a finetuned BERT model. The BERT model obtained the best performance with a mean accuracy of 88.45% on the test dataset. Our experiments support the conclusion that Natural Language Processing (NLP) models are an appropriate choice for early vulnerability detection systems in order to extract relevant information from cybersecurity news articles. |
| DOI | 10.1109/RoEduNet51892.2020.9324852 |
| Citation Key | iorga_early_2020 |
Early Detection of Vulnerabilities from News Websites using Machine Learning Models