index=dns sourcetype="stream:dns" query_type IN ("A", "AAAA", "TXT", "CNAME", "MX")
| eval domain_parts = split(query, ".")
| eval subdomain = mvindex(domain_parts, 0, mvcount(domain_parts)-3)
| eval subdomain_str = mvjoin(subdomain, ".")
| eval subdomain_len = len(subdomain_str)
| eval tld = mvindex(domain_parts, -1)
| eval registered_domain = mvindex(domain_parts, -2).".".tld
| where subdomain_len > 50
| stats count AS queries, dc(query) AS unique_queries,
        avg(subdomain_len) AS avg_subdomain_len,
        max(subdomain_len) AS max_subdomain_len,
        values(src_ip) AS sources
  by registered_domain
| where queries > 20
| sort - avg_subdomain_len
| table registered_domain, queries, unique_queries, avg_subdomain_len, max_subdomain_len, sources

index=dns sourcetype="stream:dns"
| eval domain_parts = split(query, ".")
| eval sld = mvindex(domain_parts, -2)
| eval sld_len = len(sld)
| eval char_count = sld_len
| eval vowels = len(replace(sld, "[^aeiou]", ""))
| eval consonants = len(replace(sld, "[^bcdfghjklmnpqrstvwxyz]", ""))
| eval digits = len(replace(sld, "[^0-9]", ""))
| eval vowel_ratio = if(char_count > 0, vowels / char_count, 0)
| eval digit_ratio = if(char_count > 0, digits / char_count, 0)
| where sld_len > 12 AND (vowel_ratio < 0.2 OR digit_ratio > 0.3)
| stats count AS queries, dc(query) AS unique_domains, values(src_ip) AS sources
  by query
| where unique_domains > 10
| sort - queries

import math
from collections import Counter

def shannon_entropy(text):
    """Calculate Shannon entropy of a string"""
    if not text:
        return 0
    counter = Counter(text.lower())
    length = len(text)
    entropy = -sum(
        (count / length) * math.log2(count / length)
        for count in counter.values()
    )
    return round(entropy, 4)

# Test with examples
normal_domain = "google"           # Low entropy
dga_domain = "x8kj2m9p4qw7n"      # High entropy
tunnel_subdomain = "aGVsbG8gd29ybGQ.evil.com"  # Base64 encoded data

print(f"Normal: {shannon_entropy(normal_domain)}")     # ~2.25
print(f"DGA:    {shannon_entropy(dga_domain)}")         # ~3.70
print(f"Tunnel: {shannon_entropy(tunnel_subdomain)}")   # ~3.50

# Threshold: entropy > 3.5 for subdomain = likely tunneling/DGA

index=dns sourcetype="stream:dns"
| eval domain_parts = split(query, ".")
| eval check_string = mvindex(domain_parts, 0)
| eval check_len = len(check_string)
| where check_len > 8
| eval chars = split(check_string, "")
| stats count AS total_chars, dc(chars) AS unique_chars by query, src_ip, check_string, check_len
| eval entropy_estimate = log(unique_chars, 2) * (unique_chars / check_len)
| where entropy_estimate > 3.5
| stats count AS high_entropy_queries, dc(query) AS unique_queries by src_ip
| where high_entropy_queries > 50
| sort - high_entropy_queries

index=dns sourcetype="stream:dns" earliest=-24h
| bin _time span=1h
| stats count AS queries, dc(query) AS unique_domains by src_ip, _time
| eventstats avg(queries) AS avg_queries, stdev(queries) AS stdev_queries by src_ip
| eval z_score = (queries - avg_queries) / stdev_queries
| where z_score > 3 OR queries > 5000
| sort - z_score
| table _time, src_ip, queries, unique_domains, avg_queries, z_score

index=dns sourcetype="stream:dns" query_type="TXT"
| stats count AS txt_queries, dc(query) AS unique_txt_domains,
        values(query) AS domains by src_ip
| where txt_queries > 100
| eval suspicion = case(
    txt_queries > 1000, "CRITICAL — Likely DNS tunneling",
    txt_queries > 500, "HIGH — Possible DNS tunneling",
    txt_queries > 100, "MEDIUM — Unusual TXT volume"
  )
| sort - txt_queries
| table src_ip, txt_queries, unique_txt_domains, suspicion

index=dns sourcetype="stream:dns"
| eval query_lower = lower(query)
| where (
    match(query_lower, "\.dnscat\.") OR
    match(query_lower, "\.dns2tcp\.") OR
    match(query_lower, "\.iodine\.") OR
    match(query_lower, "\.dnscapy\.") OR
    match(query_lower, "\.cobalt.*\.beacon") OR
    query_type="NULL" OR
    (query_type="TXT" AND len(query) > 100)
  )
| stats count by src_ip, query, query_type
| sort - count

index=proxy OR index=firewall
dest IN ("1.1.1.1", "1.0.0.1", "8.8.8.8", "8.8.4.4",
         "9.9.9.9", "149.112.112.112", "208.67.222.222")
dest_port=443
| stats sum(bytes_out) AS total_bytes, count AS connections by src_ip, dest
| where connections > 100 OR total_bytes > 10485760
| eval alert = "Possible DoH bypass — DNS queries sent over HTTPS to public resolver"
| sort - total_bytes

index=dns src_ip="192.168.1.105" query="*.evil-tunnel.com" earliest=-24h
| stats count AS dns_queries, earliest(_time) AS first_query, latest(_time) AS last_query
  by src_ip, query
| join src_ip [
    search index=sysmon EventCode=3 DestinationPort=53 Computer="WORKSTATION-042"
    | stats count AS connections, values(Image) AS processes by SourceIp
    | rename SourceIp AS src_ip
  ]
| table src_ip, query, dns_queries, first_query, last_query, processes

index=dns src_ip="192.168.1.105" query="*.evil-tunnel.com" earliest=-24h
| eval domain_parts = split(query, ".")
| eval encoded_data = mvindex(domain_parts, 0)
| eval encoded_bytes = len(encoded_data)
| eval decoded_bytes = encoded_bytes * 0.75  -- Base64 decoding factor
| stats sum(decoded_bytes) AS total_bytes_estimated, count AS total_queries,
        earliest(_time) AS first_seen, latest(_time) AS last_seen
| eval estimated_kb = round(total_bytes_estimated / 1024, 1)
| eval estimated_mb = round(total_bytes_estimated / 1048576, 2)
| eval duration_hours = round((last_seen - first_seen) / 3600, 1)
| eval rate_kbps = round(estimated_kb / (duration_hours * 3600) * 8, 2)
| table total_queries, estimated_mb, duration_hours, rate_kbps, first_seen, last_seen

DNS EXFILTRATION ANALYSIS — WORKSTATION-042
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Period:       2024-03-14 to 2024-03-15
Source:       192.168.1.105 (WORKSTATION-042, Finance Dept)

Findings:
  [CRITICAL] DNS tunneling detected to evil-tunnel[.]com
    Query Volume:       12,847 queries in 18 hours
    Avg Subdomain Len:  63 characters (normal: <20)
    Avg Entropy:        3.82 (threshold: 3.5)
    Query Types:        TXT (89%), A (11%)
    Estimated Data:     ~4.7 MB exfiltrated via DNS
    Rate:               0.58 kbps (slow drip pattern)

  [HIGH] DGA-like domains resolved
    Unique DGA Domains: 247 domains resolved
    Pattern:            15-char random alphanumeric.xyz TLD
    Entropy Range:      3.6 - 4.1

Process Attribution:
  Process:   svchost_update.exe (masquerading — not legitimate svchost)
  PID:       4892
  Parent:    explorer.exe
  Hash:      SHA256: a1b2c3d4... (VT: 34/72 malicious — Cobalt Strike beacon)

Containment:
  [DONE] Host isolated via EDR
  [DONE] Domain evil-tunnel[.]com added to DNS sinkhole
  [DONE] Incident IR-2024-0448 created