Handling uncertainty in intrusion analysis

Abstract

Intrusion analysis, i.e., the process of combing through Intrusion Detection System (IDS) alerts and audit logs to identify true successful and attempted attacks, remains a difficult problem in practical network security defense. The primary cause of this problem is the high false positive rate in IDS system sensors used to detect malicious activity. This high false positive rate is attributed to an inability to differentiate nearly certain attacks from those that are merely possible. This inefficacy has created high uncertainty in intrusion analysis and consequently causing an overwhelming amount of work for security analysts. As a solution, practitioners typically resort to a specific IDS-rules set that precisely captures specific attacks. However, this results in failure to discern other forms of the targeted attack because an attack’s polymorphism reflects human intelligence. Alternatively, the addition of generic rules so that an activity with remote indication of an attack will trigger an alert, requires the security analyst to discern true alerts from a multitude of false alerts, thus perpetuating the original problem. The perpetuity of this trade-off issue is a dilemma that has puzzled the cyber-security community for years. A solution to this dilemma includes reducing uncertainty in intrusion analysis by making IDS-nearly-certain alerts prominently discernible. Therefore, I propose alerts prioritization, which can be attained by integrating multiple methods. I use IDS alerts correlation by building attack scenarios in a ground-up manner. In addition, I use Dempster-Shafer Theory (DST), a non-traditional theory to quantify uncertainty, and I propose a new method for fusing non-independent alerts in an attack scenario. Finally, I propose usage of semi-supervised learning to capture an organization’s contextual knowledge, consequently improving prioritization. Evaluation of these approaches was conducted using multiple datasets. Evaluation results strongly indicate that the ranking provided by the approaches gives good prioritization of IDS alerts based on their likelihood of indicating true attacks.