Mapping Vulnerability Description to MITRE ATTCK Framework by LLM

Abstract As the number and complexity of cybersecurity threats continue to increase, security professionals must augment their knowledge by utilizing resources that provide insights into the attack patterns and techniques employed by attackers. This understanding allows them to better comprehend the potential impact of a vulnerability and prioritize the development of effective mitigation strategies within their organizations. Given the frequent generation of CVEs and the impossibility of manually mapping them to MITRE ATT&CK techniques, relying on automation methods such as BERT, a language model requiring training and fine-tuning becomes both expensive and time-consuming. To address this issue, our paper proposes a cost-effective approach using a general-purpose chatbot like GPT-3 to perform CVE to ATT&CK mapping, which yields similar results with lower costs and greater expandability.