from IPython.core.magic import register_cell_magic
from IPython.display import Markdown
import datetime
from datetime import date
import glob
import json
import logging
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import plotly
import warnings
from itables import init_notebook_mode, show
import itables.options as opt
opt.dom = "tpir"
opt.style = "table-layout:auto;width:auto"
init_notebook_mode(all_interactive=True, connected=True)
@register_cell_magic
def markdown(line, cell):
return Markdown(cell.format(**globals()))
logging.getLogger('matplotlib.font_manager').disabled = True
warnings.filterwarnings("ignore")
pd.set_option('display.width', 500)
pd.set_option('display.max_rows', 50)
pd.set_option('display.max_columns', 10)
row_accumulator = []
for filename in glob.glob('nvd.jsonl'):
with open(filename, 'r', encoding='utf-8') as f:
nvd_data = json.load(f)
for entry in nvd_data:
cve = entry['cve']['id']
try:
assigner = entry['cve']['sourceIdentifier']
except KeyError:
assigner = 'Missing_Data'
try:
published_date = entry['cve']['published']
except KeyError:
published_date = 'Missing_Data'
try:
attack_vector = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['attackVector']
except KeyError:
attack_vector = 'Missing_Data'
try:
attack_complexity = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['attackComplexity']
except KeyError:
attack_complexity = 'Missing_Data'
try:
privileges_required = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['privilegesRequired']
except KeyError:
privileges_required = 'Missing_Data'
try:
user_interaction = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['userInteraction']
except KeyError:
user_interaction = 'Missing_Data'
try:
scope = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['scope']
except KeyError:
scope = 'Missing_Data'
try:
confidentiality_impact = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['confidentialityImpact']
except KeyError:
confidentiality_impact = 'Missing_Data'
try:
integrity_impact = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['integrityImpact']
except KeyError:
integrity_impact = 'Missing_Data'
try:
availability_impact = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['availabilityImpact']
except KeyError:
availability_impact = 'Missing_Data'
try:
base_score = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['baseScore']
except KeyError:
base_score = '0.0'
try:
base_severity = entry['cve']['metrics']['cvssMetricV31'][0]['cvssData']['baseSeverity']
except KeyError:
base_severity = 'Missing_Data'
try:
exploitability_score = entry['cve']['metrics']['cvssMetricV31'][0]['exploitabilityScore']
except KeyError:
exploitability_score = 'Missing_Data'
try:
impact_score = entry['cve']['metrics']['cvssMetricV31'][0]['impactScore']
except KeyError:
impact_score = 'Missing_Data'
try:
cwe = entry['cve']['weaknesses'][0]['description'][0]['value']
except KeyError:
cwe = 'Missing_Data'
try:
description = entry['cve']['descriptions'][0]['value']
except IndexError:
description = ''
new_row = {
'CVE': cve,
'Published': published_date,
'AttackVector': attack_vector,
'AttackComplexity': attack_complexity,
'PrivilegesRequired': privileges_required,
'UserInteraction': user_interaction,
'Scope': scope,
'ConfidentialityImpact': confidentiality_impact,
'IntegrityImpact': integrity_impact,
'AvailabilityImpact': availability_impact,
'BaseScore': base_score,
'BaseSeverity': base_severity,
'ExploitabilityScore': exploitability_score,
'ImpactScore': impact_score,
'CWE': cwe,
'Description': description,
'Assigner' : assigner
}
if not description.startswith('rejected reason'):
row_accumulator.append(new_row)
nvd = pd.DataFrame(row_accumulator)
nvd['Published'] = pd.to_datetime(nvd['Published'])
thisyear = ((nvd['Published'] > '2000-01-01') & (nvd['Published'] < '2017-01-01'))
nvd = nvd.loc[thisyear]
nvd = nvd.sort_values(by=['Published'])
nvd = nvd.reset_index(drop=True)
nvd['BaseScore'] = pd.to_numeric(nvd['BaseScore']);
nvd['BaseScore'] = pd.to_numeric(nvd['BaseScore']);
nvd['BaseScore'] = nvd['BaseScore'].replace(0, np.NaN);
nvdcount = nvd['Published'].count()
nvdunique = nvd['Published'].nunique()
startdate = date(2000, 1, 1)
enddate = date(2016, 12, 31)
numberofdays = enddate - startdate
per_day = nvdcount/numberofdays.days
Markdown(f"Total Number of CVEs: **{nvd['CVE'].count()}**<br />Average CVEs Per Day: **{per_day.round(2)}**<br />Average CVSS Score: **{nvd['BaseScore'].mean().round(2)}**")
Total Number of CVEs: 79237
Average CVEs Per Day: 12.76
Average CVSS Score: 7.7
Month_Graph = nvd['Published'].groupby(nvd.Published.dt.to_period("M")).agg('count')
Year_Graph = nvd['Published'].groupby(nvd.Published.dt.to_period("Y")).agg('count')
Week_Graph = nvd['Published'].groupby(nvd.Published.dt.to_period("W")).agg('count')
Day_Graph = nvd['Published'].groupby(nvd.Published.dt.to_period("D")).agg('count')
cg = Year_Graph.plot.area(colormap='jet', figsize=(16, 8), title='CVEs Per Year')
plt.grid()
cg.set_ylabel("New CVEs");
cg.set_xlabel("Date");
cg = Month_Graph.plot.area(colormap='jet', figsize=(16, 8), title='CVEs Per Month')
plt.grid()
cg.set_ylabel("New CVEs");
cg.set_xlabel("Date");
cg = Week_Graph.plot.area(colormap='jet', figsize=(16, 8), title='CVEs Per Week')
plt.grid()
cg.set_ylabel("New CVEs");
cg.set_xlabel("Date");
cg = Day_Graph.plot.area(colormap='jet', figsize=(16, 8), title='CVEs Per Day')
plt.grid()
cg.set_ylabel("New CVEs");
cg.set_xlabel("Date");
nvd['BaseScore'].plot(kind="hist", colormap='jet', figsize=(16, 8), title='CVSS Scores');
nvd_frequency = nvd['Assigner'].value_counts()
nvd_frequency = nvd_frequency.reset_index()
nvd_frequency.columns = ['Assigner', 'CVEs']
nvd_frequency['Percentage'] = round((nvd_frequency['CVEs'] /
nvd_frequency['CVEs'].sum()) * 100)
nvd_frequency[nvd_frequency.CVEs > 100].head(50)
nvd_frequency_no_mitre = nvd_frequency[~nvd_frequency.Assigner.str.contains('cve@mitre.org')]
nvd_frequency_no_mitre = nvd_frequency_no_mitre[nvd_frequency_no_mitre.CVEs > 1].head(20)
plt.figure(figsize=(10,10))
plt.barh("Assigner", "CVEs", data = nvd_frequency_no_mitre, color="#001d82")
plt.xlabel("CVEs");
plt.ylabel("") ;
plt.title("Top 20 CNAs");
nvd_cwe = nvd['CWE'].value_counts()
nvd_cwe = nvd_cwe.reset_index()
nvd_cwe.columns = ['CWE', 'CVEs']
nvd_cwe_graph = nvd_cwe[nvd_cwe.CVEs > 100].head(25)
plt.figure(figsize=(10,10));
plt.barh("CWE", "CVEs", data = nvd_cwe_graph, color="#001d82");
plt.xlabel("CVEs");
plt.ylabel("CWE") ;
plt.title("Most Common CWE in CVE Records");
show(nvd_frequency, scrollY="400px", scrollCollapse=True, paging=False)
Assigner | CVEs | Percentage |
---|---|---|
Loading... (need help?) |
show(nvd_cwe, scrollY="400px", scrollCollapse=True, paging=False)
CWE | CVEs |
---|---|
Loading... (need help?) |
yg_df = pd.DataFrame(Year_Graph)
yg_df.columns = ['Count']
yg_df.reset_index()
show(yg_df, scrollY="400px", scrollCollapse=True, paging=False)
Count | |
---|---|
Published | |
Loading... (need help?) |
print("CVE-1999:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-1999-')]))
print("CVE-2000:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2000-')]))
print("CVE-2001:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2001-')]))
print("CVE-2002:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2002-')]))
print("CVE-2003:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2003-')]))
print("CVE-2004:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2004-')]))
print("CVE-2005:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2005-')]))
print("CVE-2006:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2006-')]))
print("CVE-2007:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2007-')]))
print("CVE-2008:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2008-')]))
print("CVE-2009:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2009-')]))
print("CVE-2010:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2010-')]))
print("CVE-2011:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2011-')]))
print("CVE-2012:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2012-')]))
print("CVE-2013:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2013-')]))
print("CVE-2014:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2014-')]))
print("CVE-2015:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2015-')]))
print("CVE-2016:\t%s" % len(nvd[nvd['CVE'].str.contains('CVE-2016-')]))
CVE-1999: 53 CVE-2000: 1151 CVE-2001: 1539 CVE-2002: 2371 CVE-2003: 1519 CVE-2004: 2671 CVE-2005: 4686 CVE-2006: 7047 CVE-2007: 6510 CVE-2008: 7034 CVE-2009: 4888 CVE-2010: 4951 CVE-2011: 4441 CVE-2012: 5200 CVE-2013: 5713 CVE-2014: 7474 CVE-2015: 6402 CVE-2016: 5587
Markdown(f"This report is updated automatically every day, last generated on: **{datetime.datetime.now()}**")
This report is updated automatically every day, last generated on: 2024-04-25 12:07:06.581180