To adapt to the rapidly evolving cyberattacks, cyber threat knowledge is essential for organizations to gain visibility into the fast-evolving threat landscape and timely identify early signs of an attack and the adversary’s strategies, tactics, and techniques. In addition, to gaining insight into potential cyber threats, hacker forums are a valuable source. However, the complexity and diversity of the content in hacker forums make it challenging to retrieve useful cybersecurity information. This research proposes an improved data preprocessing method to reduce feature dimension and a hybrid method combining text tagging and clustering analysis techniques to discover cybersecurity information from unstructured hacker forums. The experimental results illustrate that the proposed solution could extract cybersecurity information efficiently.
International Journal of Network Security 23(6), pp.1126-1138