ma_cisco_malware/dataset.py

# -*- coding: utf-8 -*-
import string

import numpy as np
import pandas as pd
from tqdm import tqdm


def get_character_dict():
    return dict((char, idx) for (idx, char) in
                enumerate(string.ascii_lowercase + string.punctuation))


def get_user_chunks(dataFrame, windowSize=10, overlapping=False,
                    maxLengthInSeconds=300):
    # print('maxLength: ' + str(maxLengthInSeconds))
    maxMilliSeconds = maxLengthInSeconds * 1000
    outDomainLists = []
    outDFFrames = []
    if overlapping == False:
        numBlocks = int(np.ceil(float(len(dataFrame)) / float(windowSize)))
        userIDs = np.arange(len(dataFrame))
        for blockID in np.arange(numBlocks):
            curIDs = userIDs[(blockID * windowSize):((blockID + 1) * windowSize)]
            # print(curIDs)
            useData = dataFrame.iloc[curIDs]
            curDomains = useData['domain']
            if maxLengthInSeconds != -1:
                curMinMilliSeconds = np.min(useData['timeStamp']) + maxMilliSeconds
                underTimeOutIDs = np.where(np.array(useData['timeStamp']) <= curMinMilliSeconds)
                if len(underTimeOutIDs) != len(curIDs):
                    curIDs = curIDs[underTimeOutIDs]
                    useData = dataFrame.iloc[curIDs]
                    curDomains = useData['domain']
            outDomainLists.append(list(curDomains))
            outDFFrames.append(useData)
    else:
        numBlocks = len(dataFrame) + 1 - windowSize
        userIDs = np.arange(len(dataFrame))
        for blockID in np.arange(numBlocks):
            curIDs = userIDs[blockID:blockID + windowSize]
            # print(curIDs)
            useData = dataFrame.iloc[curIDs]
            curDomains = useData['domain']
            if maxLengthInSeconds != -1:
                curMinMilliSeconds = np.min(useData['timeStamp']) + maxMilliSeconds
                underTimeOutIDs = np.where(np.array(useData['timeStamp']) <= curMinMilliSeconds)
                if len(underTimeOutIDs) != len(curIDs):
                    curIDs = curIDs[underTimeOutIDs]
                    useData = dataFrame.iloc[curIDs]
                    curDomains = useData['domain']
            outDomainLists.append(list(curDomains))
            outDFFrames.append(useData)
    return (outDomainLists, outDFFrames)


def get_domain_features(domain, vocab, max_length=40):
    curFeature = np.zeros([max_length, ])
    for j in range(np.min([len(domain), max_length])):
        curCharacter = domain[-j]
        if curCharacter in vocab:
            curFeature[j] = vocab[curCharacter]
    return curFeature


def get_flow_features(flow):
    useKeys = ['duration', 'bytes_down', 'bytes_up']
    curFeature = np.zeros([len(useKeys), ])
    for i, curKey in enumerate(useKeys):
        try:
            curFeature[i] = np.log1p(flow[curKey]).astype(float)
        except:
            pass
    return curFeature


def getCiscoFeatures(curDataLine, urlSIPDict):
    numCiscoFeatures = 30
    try:
        ciscoFeatures = urlSIPDict[str(curDataLine['domain']) + str(curDataLine['server_ip'])]
        # log transform
        ciscoFeatures = np.log1p(ciscoFeatures).astype(float)
        return ciscoFeatures.ravel()
    except:
        return np.zeros([numCiscoFeatures, ]).ravel()


def create_dataset_from_flows(user_flow_df, char_dict, maxLen, threshold=3, windowSize=10, use_cisco_features=False):
    domainLists = []
    dfLists = []
    print("get chunks from user data frames")
    for i, user_flow in enumerate(get_flow_per_user(user_flow_df)):
        (domainListsTmp, dfListsTmp) = get_user_chunks(user_flow, windowSize=windowSize,
                                                       overlapping=True, maxLengthInSeconds=-1)
        domainLists += domainListsTmp
        dfLists += dfListsTmp
        if i >= 10:
            break

    print("create training dataset")
    return create_dataset_from_lists(
        domains=domainLists, dfs=dfLists, charachterDict=char_dict,
        maxLen=maxLen, threshold=threshold,
        use_cisco_features=use_cisco_features, urlSIPDIct=dict(),
        windowSize=windowSize)


def create_dataset_from_lists(domains, dfs, charachterDict, maxLen, threshold=3,
                              use_cisco_features=False, urlSIPDIct=dict(),
                              windowSize=10):
    if 'hits' in dfs[0].keys():
        hitName = 'hits'
    elif 'virusTotalHits' in dfs[0].keys():
        hitName = 'virusTotalHits'
    numFlowFeatures = 3
    numCiscoFeatures = 30
    numFeatures = numFlowFeatures
    if use_cisco_features:
        numFeatures += numCiscoFeatures
    outputFeatures = []
    label = []
    hits = []
    trainNames = []
    for i in range(windowSize):
        outputFeatures.append(np.zeros([len(domains), maxLen]))
        outputFeatures.append(np.zeros([len(domains), numFeatures]))

    for i in tqdm(np.arange(len(domains)), miniters=10):
        curCounter = 0
        # print('len domainList: ' + str(len(domainLists[i])))
        # print('len df: ' + str(len(dfLists[i])))
        for j in range(np.min([windowSize, len(domains[i])])):
            outputFeatures[curCounter][i, :] = get_domain_features(domains[i][j], charachterDict, maxLen)
            curCounter += 1
            if use_cisco_features:
                outputFeatures[curCounter][i, 0:numFlowFeatures] = get_flow_features(dfs[i].iloc[j])
                outputFeatures[curCounter][i, numFlowFeatures:] = get_cisco_features(dfs[i].iloc[j], urlSIPDIct)
            else:
                outputFeatures[curCounter][i, :] = get_flow_features(dfs[i].iloc[j])
            curCounter += 1
        curLabel = 0.0
        if np.max(dfs[i][hitName]) >= threshold:
            curLabel = 1.0
        elif np.max(dfs[i][hitName]) == -1:
            curLabel = -1.0
        elif np.max(dfs[i][hitName]) > 0 and np.max(dfs[i][hitName]) < threshold:
            curLabel = -2.0
        label.append(curLabel)
        hits.append(np.max(dfs[i][hitName]))
        trainNames.append(np.unique(dfs[i]['user_hash']))
    return (outputFeatures, np.array(label), np.array(hits), np.array(trainNames))


def get_user_flow_data():
    df = pd.read_csv("data/rk_data.csv.gz")
    df.drop("Unnamed: 0", 1, inplace=True)
    df.set_index(keys=['user_hash'], drop=False, inplace=True)
    return df


def get_flow_per_user(df):
    users = df['user_hash'].unique().tolist()
    for user in users:
        yield df.loc[df.user_hash == user]