Tracing CAPEC attack patterns from CVE vulnerability information using natural language processing technique

To effectively respond to vulnerabilities, information must not only be collected efficiently and quickly but also the vulnerability and the attack techniques must be understood. A security knowledge repository can collect such information. The Common Vulnerabilities and Exposures (CVE) provides known vulnerabilities of products, while the Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit known weaknesses. Because the information in these two repositories is not directly related, identifying the related CAPEC attack information from the CVE vulnerability information is challenging. One proposed method traces some related CAPEC-ID from CVE-ID through Common Weakness Enumeration (CWE). However, it is not applicable to all patterns. Here, we propose a method to automatically trace the related CAPEC-IDs from CVE-ID using TF-IDF and Doc2Vec. Additionally, we experimentally confirm that TF-IDF is more accurate than Doc2vec.