vtTool.py 文件源码

def clusterMalwareNames(malwareNames):
    # strictly lexical clustering over malware-names
    wordCount = {}
    # create a distance matrix
    matrix = np.zeros((len(malwareNames), len(malwareNames)))
    for i in range(len(malwareNames)):
        for j in range(len(malwareNames)):
            if matrix[i, j] == 0.0:        
                matrix[i, j] = computeSimilarity(malwareNames[i], malwareNames[j])
                matrix[j, i] = matrix[i, j]

    # Scikit-Learn's DBSCAN implementation to cluster the malware-names
    clust = DBSCAN(eps=0.1, min_samples=5, metric="precomputed")
    clust.fit(matrix)    

    preds = clust.labels_
    clabels = np.unique(preds)

    # create Word-Count Map
    for i in range(clabels.shape[0]):
        if clabels[i] < 0:
            continue

        cmem_ids = np.where(preds == clabels[i])[0]
        cmembers = []

        for cmem_id in cmem_ids:
            cmembers.append(malwareNames[cmem_id])

        wordCount[", ".join(uniqueList(cmembers))] = len(cmem_ids)
    return wordCount