A parameter-free hybrid clustering algorithm used for malware categorization

摘要: Nowadays, numerous attacks made by the malware, such as viruses, backdoors, spyware, trojans and worms, have presented a major security threat to computer users. The most significant line of defense against malware is anti-virus products which detects, removes, characterizes these threats. ability AV successfully characterize threats greatly depends on method for categorizing profiles into groups. Therefore, clustering different families one topics that are great interest. In this paper, resting analysis extracted instruction samples, we propose novel parameter-free hybrid algorithm (PFHC) combines merits hierarchical K-means algorithms clustering. It can not only generate stable initial division, but also give best K. PFHC first utilizes agglomerative frame, starting with N singleton clusters, each exactly includes sample, then reuses centroids upper level in every merges two nearest finally adopts iteration achieve an approximate global optimal division. evaluates validity procedure generates K comparing values. promising studies real daily data collection illustrate that, compared popular existing approaches, our proposed always much higher quality clusters it be well used categorization.