232 lines
10 KiB
SQL
232 lines
10 KiB
SQL
-- ============================================================================
|
|
-- SCRIPT DE DÉPLOIEMENT DES VUES DE DÉTECTION (CLICKHOUSE) - MABASE_PROD
|
|
-- ============================================================================
|
|
|
|
DROP TABLE IF EXISTS mabase_prod.ml_detected_anomalies;
|
|
DROP VIEW IF EXISTS mabase_prod.view_ai_features_1h;
|
|
DROP VIEW IF EXISTS mabase_prod.view_host_ip_ja4_rotation;
|
|
DROP VIEW IF EXISTS mabase_prod.view_host_ja4_anomalies;
|
|
DROP VIEW IF EXISTS mabase_prod.view_form_bruteforce_detected;
|
|
DROP VIEW IF EXISTS mabase_prod.view_alpn_mismatch_detected;
|
|
DROP VIEW IF EXISTS mabase_prod.view_tcp_spoofing_detected;
|
|
DROP VIEW IF EXISTS mabase_prod.mv_agg_host_ip_ja4_1h;
|
|
DROP TABLE IF EXISTS mabase_prod.agg_host_ip_ja4_1h;
|
|
DROP VIEW IF EXISTS mabase_prod.mv_agg_header_fingerprint_1h;
|
|
DROP TABLE IF EXISTS mabase_prod.agg_header_fingerprint_1h;
|
|
|
|
-- ----------------------------------------------------------------------------
|
|
-- 1. TABLES D'AGRÉGATION ET VUES MATÉRIALISÉES
|
|
-- ----------------------------------------------------------------------------
|
|
|
|
CREATE TABLE mabase_prod.agg_host_ip_ja4_1h (
|
|
window_start DateTime,
|
|
src_ip String,
|
|
ja4 String,
|
|
host String,
|
|
first_seen SimpleAggregateFunction(min, DateTime),
|
|
last_seen SimpleAggregateFunction(max, DateTime),
|
|
hits SimpleAggregateFunction(sum, UInt64),
|
|
count_post SimpleAggregateFunction(sum, UInt64),
|
|
uniq_paths AggregateFunction(uniq, String),
|
|
uniq_query_params AggregateFunction(uniq, String),
|
|
src_country_code SimpleAggregateFunction(any, String),
|
|
tcp_fingerprint SimpleAggregateFunction(any, String),
|
|
tcp_jitter_variance AggregateFunction(varPop, Float64),
|
|
tcp_window_size SimpleAggregateFunction(any, UInt32),
|
|
tcp_window_scale SimpleAggregateFunction(any, UInt32),
|
|
tcp_mss SimpleAggregateFunction(any, UInt32),
|
|
tcp_ttl SimpleAggregateFunction(any, UInt32),
|
|
http_version SimpleAggregateFunction(any, String),
|
|
tls_alpn SimpleAggregateFunction(any, String),
|
|
tls_sni SimpleAggregateFunction(any, String),
|
|
first_ua SimpleAggregateFunction(any, String),
|
|
correlated SimpleAggregateFunction(max, UInt8),
|
|
unique_src_ports AggregateFunction(uniq, UInt16),
|
|
max_keepalives SimpleAggregateFunction(max, UInt32),
|
|
orphan_count SimpleAggregateFunction(sum, UInt64)
|
|
) ENGINE = AggregatingMergeTree()
|
|
ORDER BY (window_start, src_ip, ja4, host)
|
|
TTL window_start + INTERVAL 7 DAY;
|
|
|
|
CREATE MATERIALIZED VIEW mabase_prod.mv_agg_host_ip_ja4_1h TO mabase_prod.agg_host_ip_ja4_1h AS
|
|
SELECT
|
|
toStartOfHour(src.time) AS window_start,
|
|
src.src_ip, src.ja4, src.host,
|
|
min(src.time) AS first_seen, max(src.time) AS last_seen,
|
|
count() AS hits,
|
|
sum(IF(src.method = 'POST', 1, 0)) AS count_post,
|
|
uniqState(src.path) AS uniq_paths,
|
|
uniqState(src.query) AS uniq_query_params,
|
|
any(src.src_country_code) AS src_country_code,
|
|
any(toString(cityHash64(concat(toString(src.tcp_meta_window_size), toString(src.tcp_meta_mss), toString(src.tcp_meta_window_scale), src.tcp_meta_options)))) AS tcp_fingerprint,
|
|
varPopState(toFloat64(src.syn_to_clienthello_ms)) AS tcp_jitter_variance,
|
|
any(src.tcp_meta_window_size) AS tcp_window_size,
|
|
any(src.tcp_meta_window_scale) AS tcp_window_scale,
|
|
any(src.tcp_meta_mss) AS tcp_mss,
|
|
any(src.ip_meta_ttl) AS tcp_ttl,
|
|
any(src.http_version) AS http_version,
|
|
any(src.tls_alpn) AS tls_alpn,
|
|
any(src.tls_sni) AS tls_sni,
|
|
any(src.header_user_agent) AS first_ua,
|
|
max(toUInt8(src.correlated)) AS correlated,
|
|
uniqState(toUInt16(src.src_port)) AS unique_src_ports,
|
|
max(toUInt32(src.keepalives)) AS max_keepalives,
|
|
sum(IF(src.orphan_side = 'A' OR toUInt8(src.correlated) = 0, 1, 0)) AS orphan_count
|
|
FROM mabase_prod.http_logs AS src
|
|
GROUP BY window_start, src.src_ip, src.ja4, src.host;
|
|
|
|
CREATE TABLE mabase_prod.agg_header_fingerprint_1h (
|
|
window_start DateTime,
|
|
src_ip String,
|
|
header_order_hash SimpleAggregateFunction(any, String),
|
|
header_count SimpleAggregateFunction(max, UInt16),
|
|
has_accept_language SimpleAggregateFunction(max, UInt8),
|
|
has_cookie SimpleAggregateFunction(max, UInt8),
|
|
has_referer SimpleAggregateFunction(max, UInt8), -- NOUVEAU (JA4H_a)
|
|
modern_browser_score SimpleAggregateFunction(max, UInt8),
|
|
sec_fetch_mode SimpleAggregateFunction(any, String),
|
|
sec_fetch_dest SimpleAggregateFunction(any, String),
|
|
count_site_none SimpleAggregateFunction(sum, UInt64)
|
|
) ENGINE = AggregatingMergeTree()
|
|
ORDER BY (window_start, src_ip)
|
|
TTL window_start + INTERVAL 7 DAY;
|
|
|
|
CREATE MATERIALIZED VIEW mabase_prod.mv_agg_header_fingerprint_1h TO mabase_prod.agg_header_fingerprint_1h AS
|
|
SELECT
|
|
toStartOfHour(src.time) AS window_start,
|
|
src.src_ip,
|
|
any(toString(cityHash64(src.client_headers))) AS header_order_hash,
|
|
max(toUInt16(length(src.client_headers) - length(replaceAll(src.client_headers, ',', '')) + 1)) AS header_count,
|
|
max(toUInt8(if(position(src.client_headers, 'Accept-Language') > 0, 1, 0))) AS has_accept_language,
|
|
max(toUInt8(if(position(src.client_headers, 'Cookie') > 0, 1, 0))) AS has_cookie,
|
|
max(toUInt8(if(position(src.client_headers, 'Referer') > 0, 1, 0))) AS has_referer, -- NOUVEAU (JA4H_a)
|
|
max(toUInt8(if(length(src.header_sec_ch_ua) > 0, 100, if(length(src.header_user_agent) > 0, 50, 0)))) AS modern_browser_score,
|
|
any(src.header_sec_fetch_mode) AS sec_fetch_mode,
|
|
any(src.header_sec_fetch_dest) AS sec_fetch_dest,
|
|
sum(IF(src.header_sec_fetch_site = 'none', 1, 0)) AS count_site_none
|
|
FROM mabase_prod.http_logs AS src
|
|
GROUP BY window_start, src.src_ip;
|
|
|
|
-- ----------------------------------------------------------------------------
|
|
-- 2. TABLE DES ANOMALIES ÉLARGIE POUR GRAFANA
|
|
-- ----------------------------------------------------------------------------
|
|
CREATE TABLE mabase_prod.ml_detected_anomalies (
|
|
detected_at DateTime,
|
|
src_ip String,
|
|
ja4 String,
|
|
host String,
|
|
anomaly_score Float32,
|
|
|
|
-- Dimensions Applicatives et Comportementales
|
|
hits UInt64,
|
|
hit_velocity Float32,
|
|
fuzzing_index Float32,
|
|
post_ratio Float32,
|
|
site_none_ratio Float32,
|
|
|
|
-- Dimensions Réseau / TCP
|
|
port_exhaustion_ratio Float32,
|
|
max_keepalives UInt32,
|
|
orphan_ratio Float32,
|
|
tcp_jitter_variance Float32,
|
|
tcp_shared_count UInt32,
|
|
true_window_size UInt64,
|
|
window_mss_ratio Float32,
|
|
|
|
-- Dimensions TLS / Contextuelles
|
|
alpn_http_mismatch UInt8,
|
|
is_alpn_missing UInt8,
|
|
sni_host_mismatch UInt8,
|
|
|
|
-- Dimensions JA4H (Headers)
|
|
header_count UInt16,
|
|
has_accept_language UInt8,
|
|
has_cookie UInt8,
|
|
has_referer UInt8,
|
|
modern_browser_score UInt8,
|
|
is_headless UInt8,
|
|
header_order_shared_count UInt32, -- NOUVEAU (JA4H_b)
|
|
|
|
reason String
|
|
) ENGINE = MergeTree()
|
|
ORDER BY (detected_at, src_ip, ja4)
|
|
TTL detected_at + INTERVAL 30 DAY;
|
|
|
|
-- ----------------------------------------------------------------------------
|
|
-- 3. VUE DE FEATURE ENGINEERING POUR L'IA (SUR 24H)
|
|
-- ----------------------------------------------------------------------------
|
|
CREATE OR REPLACE VIEW mabase_prod.view_ai_features_1h AS
|
|
SELECT
|
|
a.src_ip, a.ja4, a.host, a.hits, a.uniq_paths, a.uniq_query_params, a.count_post,
|
|
a.correlated AS correlated,
|
|
|
|
(a.count_post / (a.hits + 1)) AS post_ratio,
|
|
(a.uniq_query_params / (a.uniq_paths + 1)) AS fuzzing_index,
|
|
(a.hits / (dateDiff('second', a.first_seen, a.last_seen) + 1)) AS hit_velocity,
|
|
(a.unique_src_ports / (a.hits + 1)) AS port_exhaustion_ratio,
|
|
(a.orphan_count / (a.hits + 1)) AS orphan_ratio,
|
|
a.max_keepalives AS max_keepalives,
|
|
|
|
COALESCE(a.tcp_jitter_variance, 0) AS tcp_jitter_variance,
|
|
count() OVER (PARTITION BY a.tcp_fingerprint) AS tcp_shared_count,
|
|
a.tcp_window_size * exp2(a.tcp_window_scale) AS true_window_size,
|
|
IF(a.tcp_mss > 0, a.tcp_window_size / a.tcp_mss, 0) AS window_mss_ratio,
|
|
|
|
IF(a.tls_alpn = 'h2' AND a.http_version!= '2', 1, 0) AS alpn_http_mismatch,
|
|
IF(length(a.tls_alpn) = 0 OR a.tls_alpn = '00', 1, 0) AS is_alpn_missing,
|
|
IF(length(a.tls_sni) > 0 AND a.tls_sni!= a.host, 1, 0) AS sni_host_mismatch,
|
|
|
|
COALESCE(h.header_count, 0) AS header_count,
|
|
COALESCE(h.has_accept_language, 0) AS has_accept_language,
|
|
COALESCE(h.has_cookie, 0) AS has_cookie,
|
|
COALESCE(h.has_referer, 0) AS has_referer,
|
|
COALESCE(h.modern_browser_score, 0) AS modern_browser_score,
|
|
IF(h.sec_fetch_mode = 'navigate' AND h.sec_fetch_dest!= 'document', 1, 0) AS is_fake_navigation,
|
|
(h.count_site_none / (a.hits + 1)) AS site_none_ratio,
|
|
|
|
-- JA4H_b : Regroupement par ordre de header pour détecter les botnets
|
|
count() OVER (PARTITION BY h.header_order_hash) AS header_order_shared_count
|
|
|
|
FROM (
|
|
SELECT
|
|
window_start, src_ip, ja4, host,
|
|
sum(hits) AS hits,
|
|
uniqMerge(uniq_paths) AS uniq_paths,
|
|
uniqMerge(uniq_query_params) AS uniq_query_params,
|
|
sum(count_post) AS count_post,
|
|
min(first_seen) AS first_seen,
|
|
max(last_seen) AS last_seen,
|
|
any(tcp_fingerprint) AS tcp_fingerprint,
|
|
varPopMerge(tcp_jitter_variance) AS tcp_jitter_variance,
|
|
any(tcp_window_size) AS tcp_window_size,
|
|
any(tcp_window_scale) AS tcp_window_scale,
|
|
any(tcp_mss) AS tcp_mss,
|
|
any(http_version) AS http_version,
|
|
any(tls_alpn) AS tls_alpn,
|
|
any(tls_sni) AS tls_sni,
|
|
max(correlated) AS correlated,
|
|
uniqMerge(unique_src_ports) AS unique_src_ports,
|
|
max(max_keepalives) AS max_keepalives,
|
|
sum(orphan_count) AS orphan_count
|
|
FROM mabase_prod.agg_host_ip_ja4_1h
|
|
WHERE window_start >= toStartOfHour(now() - INTERVAL 24 HOUR)
|
|
GROUP BY window_start, src_ip, ja4, host
|
|
) a
|
|
LEFT JOIN (
|
|
SELECT
|
|
window_start, src_ip,
|
|
any(header_order_hash) AS header_order_hash,
|
|
max(header_count) AS header_count,
|
|
max(has_accept_language) AS has_accept_language,
|
|
max(has_cookie) AS has_cookie,
|
|
max(has_referer) AS has_referer,
|
|
max(modern_browser_score) AS modern_browser_score,
|
|
any(sec_fetch_mode) AS sec_fetch_mode,
|
|
any(sec_fetch_dest) AS sec_fetch_dest,
|
|
sum(count_site_none) AS count_site_none
|
|
FROM mabase_prod.agg_header_fingerprint_1h
|
|
WHERE window_start >= toStartOfHour(now() - INTERVAL 24 HOUR)
|
|
GROUP BY window_start, src_ip
|
|
) h
|
|
ON a.src_ip = h.src_ip AND a.window_start = a.window_start;
|