Masquerade Detection by Using Activity Patterns

Masqueraders in computer intrusion detection are people who use somebody else’s computer account. The typical approach is based on the idea that masquerader activity is unusual activity that will manifest as significant excursions from normal user profiles. When a deviation from normal behavior is observed, a masquerade attempt is suspected. This paper proposes a statistical approach for detecting masqueraders by tracing the activity patterns of the users. A probabilistic activity matrix is created for each user, which, will be used for detection of masquerading.