In this paper, we study the problem of employ ensemble learning for computer forensic. We propose a Lazy Local Learning based bagging (L3B) approach, where base learners are trained from a small instance subset surrounding each test instance. More specifically, given a test instance x, L3B first discovers x\'s k nearest neighbours, and then applies progressive sampling to the selected neighbours to train a set of base classifiers, by using a given very weak (VW) learner. At the last stage, x is labeled as the most frequently voted class of all base classifiers. Finally, we apply the proposed L3B to computer forensic.