code_public/ja4-platform
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(sql): contournement bug scope ClickHouse 24.8 dans view_ai_features_1h

Browse Source 
- Restructure 07_ai_features_view.sql : single anonymous inner subquery
  avec aliases explicites sur toutes les colonnes (a.xxx AS xxx, h.xxx AS xxx,
  h2.xxx AS xxx) pour résoudre l'ambiguïté PARTITION BY src_ip dans l'outer SELECT
- Supprime les CTEs multiples (h2_agg, enriched) qui déclenchaient le bug
- Fix migration 04_http2_fields.sql : ordre DEFAULT avant CODEC (syntax ClickHouse)
- make init-stack : 0 erreur sur 13 fichiers SQL

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
This commit is contained in:
toto
2026-04-10 00:48:05 +02:00
parent a108814a56
commit 2f2c5e03bb
2 changed files with 232 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

400
shared/clickhouse/07_ai_features_view.sql
View File

@ -1,219 +1,277 @@
-- =============================================================================
-- 07_ai_features_view.sql — AI feature view with full Anubis enrichment
-- Source: bot_detector/anubis/view_ai_features_anubis.sql
-- Includes combined UA+IP priority logic and Anubis bot_name/action/category.
-- §2 : Features HTTP/2 (dict_browser_h2, cohérence H2↔JA4, pseudo-headers)
-- §3 : Score de cohérence de fingerprint cross-layer
-- Note: single anonymous inner subquery with explicit aliases (fix ClickHouse 24.8
-- scope bug where PARTITION BY src_ip fails when multiple JOIN sources expose src_ip)
-- =============================================================================
CREATE OR REPLACE VIEW ja4_processing.view_ai_features_1h AS
WITH
-- §2 — Agrégation des fingerprints HTTP/2 par (heure, src_ip)
-- Lecture directe depuis http_logs pour les colonnes ajoutées à l'étape 1
h2_agg AS (
WITH base_data AS (
SELECT
toStartOfHour(time) AS window_start,
toIPv6(src_ip) AS src_ip,
anyIf(h2_fingerprint, h2_fingerprint != '') AS h2_fp,
anyIf(h2_pseudo_order, h2_pseudo_order != '') AS h2_pseudo_ord
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 24 HOUR
AND (h2_fingerprint != '' OR h2_pseudo_order != '')
GROUP BY window_start, src_ip
),
base_data AS (
SELECT
a.window_start, a.src_ip, a.ja4, a.host,
toString(a.src_asn) AS asn_number,
a.src_as_name AS asn_org, a.src_org AS asn_detail, a.src_domain AS asn_domain,
a.src_country_code AS country_code,
dictGetOrDefault('ja4_processing.dict_asn_reputation', 'label', toUInt64(a.src_asn), 'unknown') AS asn_label,
window_start, src_ip, ja4, host,
toString(src_asn) AS asn_number,
src_as_name AS asn_org, src_org AS asn_detail, src_domain AS asn_domain,
src_country_code AS country_code,
dictGetOrDefault('ja4_processing.dict_asn_reputation', 'label', toUInt64(src_asn), 'unknown') AS asn_label,
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ip', 'bot_name', a.src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ja4', 'bot_name', tuple(a.ja4), ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ip', 'bot_name', src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_bot_ja4', 'bot_name', tuple(ja4), ''), ''),
''
) AS bot_name,
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(a.ja4), '') AS browser_family,
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(ja4), '') AS browser_family,
-- Anubis: IP/CIDR > ASN (simplified — UA and Country rules removed)
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', a.src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(a.src_asn), ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'bot_name', src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'bot_name', toUInt32(src_asn), ''), ''),
''
) AS anubis_bot_name,
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', a.src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', toUInt32(a.src_asn), ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'action', src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'action', toUInt32(src_asn), ''), ''),
''
) AS anubis_bot_action,
COALESCE(
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', a.src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', toUInt32(a.src_asn), ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_ip', 'category', src_ip, ''), ''),
nullIf(dictGetOrDefault('ja4_processing.dict_anubis_asn', 'category', toUInt32(src_asn), ''), ''),
''
) AS anubis_bot_category,
a.hits AS hits,
sum(a.hits) OVER (PARTITION BY a.src_ip) AS total_ip_hits,
a.correlated AS correlated,
a.tcp_jitter_variance AS tcp_jitter_variance,
a.true_window_size AS true_window_size,
a.window_mss_ratio AS window_mss_ratio,
a.max_keepalives AS max_keepalives,
h.header_order_hash AS header_order_hash, h.header_count AS header_count,
h.has_accept_language AS has_accept_language, h.has_cookie AS has_cookie,
h.has_referer AS has_referer, h.modern_browser_score AS modern_browser_score,
h.has_sec_ch_ua AS has_sec_ch_ua,
h.ua_ch_mismatch AS ua_ch_mismatch,
(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.ip_id_zero_count / (a.hits + 1)) AS ip_id_zero_ratio,
(a.hits / (a.unique_conn_id + 1)) AS multiplexing_efficiency,
IF(a.mss_1460_count > (a.hits * 0.8) AND h.has_sec_ch_ua > 0, 1, 0) AS mss_mobile_mismatch,
a.request_size_variance AS request_size_variance,
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,
IF(h.sec_fetch_mode = 'navigate' AND h.sec_fetch_dest != 'document', 1, 0) AS is_fake_navigation,
count() OVER (PARTITION BY a.tcp_fingerprint) AS tcp_shared_count,
count() OVER (PARTITION BY h.header_order_hash) AS header_order_shared_count,
(a.count_assets / (a.hits + 1)) AS asset_ratio,
(a.count_no_referer / (a.hits + 1)) AS direct_access_ratio,
IF(a.unique_ua > 2, 1, 0) AS is_ua_rotating,
uniqExact(a.ja4) OVER (PARTITION BY a.src_ip) AS distinct_ja4_count,
((a.hits / (a.unique_src_ports + 1)) / (dateDiff('second', a.first_seen, a.last_seen) + 1)) AS src_port_density,
(sum(a.hits) OVER (PARTITION BY a.ja4, a.src_asn) / (sum(a.hits) OVER (PARTITION BY a.ja4) + 1)) AS ja4_asn_concentration,
(sum(a.hits) OVER (PARTITION BY a.ja4, a.src_country_code) / (sum(a.hits) OVER (PARTITION BY a.ja4) + 1)) AS ja4_country_concentration,
IF(sum(a.hits) OVER (PARTITION BY a.ja4) < 100, 1, 0) AS is_rare_ja4,
(count() OVER (PARTITION BY h.header_order_hash, a.ja4) / (count() OVER (PARTITION BY a.ja4) + 1)) AS header_order_confidence,
uniqExact(h.header_order_hash) OVER (PARTITION BY a.src_ip) AS distinct_header_orders,
(a.uniq_paths / (a.hits + 1)) AS path_diversity_ratio,
a.url_depth_variance AS url_depth_variance,
(a.count_anomalous_payload / (a.hits + 1)) AS anomalous_payload_ratio,
a.uniq_ja3_val AS uniq_ja3_per_row,
sqrt(a.tcp_jitter_variance) / greatest(a.avg_syn_ms_val, 1) AS syn_timing_cv,
a.tls12_count / (a.hits + 1) AS tls12_ratio,
a.count_head / (a.hits + 1) AS head_ratio,
a.count_no_sec_fetch / (a.hits + 1) AS sec_fetch_absence_rate,
a.count_generic_accept / (a.hits + 1) AS generic_accept_ratio,
a.count_http10 / (a.hits + 1) AS http10_ratio,
a.ip_df_variance AS ip_df_variance,
a.avg_ttl_val AS avg_ttl,
sqrt(a.ttl_variance_val) AS ttl_std,
IF(a.count_correlated_val > 0, a.count_no_wscale_val / a.count_correlated_val, 0) AS no_window_scale_ratio,
a.count_no_accept_enc_val / (a.hits + 1) AS missing_accept_enc_ratio,
a.count_http_scheme_val / (a.hits + 1) AS http_scheme_ratio,
hits AS hits,
sum(hits) OVER (PARTITION BY src_ip) AS total_ip_hits,
correlated AS correlated,
tcp_jitter_variance AS tcp_jitter_variance,
true_window_size AS true_window_size,
window_mss_ratio AS window_mss_ratio,
max_keepalives AS max_keepalives,
header_order_hash AS header_order_hash, header_count AS header_count,
has_accept_language AS has_accept_language, has_cookie AS has_cookie,
has_referer AS has_referer, modern_browser_score AS modern_browser_score,
has_sec_ch_ua AS has_sec_ch_ua,
ua_ch_mismatch AS ua_ch_mismatch,
(count_post / (hits + 1)) AS post_ratio,
(uniq_query_params / (uniq_paths + 1)) AS fuzzing_index,
(hits / (dateDiff('second', first_seen, last_seen) + 1)) AS hit_velocity,
(unique_src_ports / (hits + 1)) AS port_exhaustion_ratio,
(orphan_count / (hits + 1)) AS orphan_ratio,
(ip_id_zero_count / (hits + 1)) AS ip_id_zero_ratio,
(hits / (unique_conn_id + 1)) AS multiplexing_efficiency,
IF(mss_1460_count > (hits * 0.8) AND has_sec_ch_ua > 0, 1, 0) AS mss_mobile_mismatch,
request_size_variance AS request_size_variance,
IF(tls_alpn = 'h2' AND http_version != '2', 1, 0) AS alpn_http_mismatch,
IF(length(tls_alpn) = 0 OR tls_alpn = '00', 1, 0) AS is_alpn_missing,
IF(length(tls_sni) > 0 AND tls_sni != host, 1, 0) AS sni_host_mismatch,
IF(sec_fetch_mode = 'navigate' AND sec_fetch_dest != 'document', 1, 0) AS is_fake_navigation,
count() OVER (PARTITION BY tcp_fingerprint) AS tcp_shared_count,
count() OVER (PARTITION BY header_order_hash) AS header_order_shared_count,
(count_assets / (hits + 1)) AS asset_ratio,
(count_no_referer / (hits + 1)) AS direct_access_ratio,
IF(unique_ua > 2, 1, 0) AS is_ua_rotating,
uniqExact(ja4) OVER (PARTITION BY src_ip) AS distinct_ja4_count,
((hits / (unique_src_ports + 1)) / (dateDiff('second', first_seen, last_seen) + 1)) AS src_port_density,
(sum(hits) OVER (PARTITION BY ja4, src_asn) / (sum(hits) OVER (PARTITION BY ja4) + 1)) AS ja4_asn_concentration,
(sum(hits) OVER (PARTITION BY ja4, src_country_code) / (sum(hits) OVER (PARTITION BY ja4) + 1)) AS ja4_country_concentration,
IF(sum(hits) OVER (PARTITION BY ja4) < 100, 1, 0) AS is_rare_ja4,
(count() OVER (PARTITION BY header_order_hash, ja4) / (count() OVER (PARTITION BY ja4) + 1)) AS header_order_confidence,
uniqExact(header_order_hash) OVER (PARTITION BY src_ip) AS distinct_header_orders,
(uniq_paths / (hits + 1)) AS path_diversity_ratio,
url_depth_variance AS url_depth_variance,
(count_anomalous_payload / (hits + 1)) AS anomalous_payload_ratio,
uniq_ja3_val AS uniq_ja3_per_row,
sqrt(tcp_jitter_variance) / greatest(avg_syn_ms_val, 1) AS syn_timing_cv,
tls12_count / (hits + 1) AS tls12_ratio,
count_head / (hits + 1) AS head_ratio,
count_no_sec_fetch / (hits + 1) AS sec_fetch_absence_rate,
count_generic_accept / (hits + 1) AS generic_accept_ratio,
count_http10 / (hits + 1) AS http10_ratio,
ip_df_variance AS ip_df_variance,
avg_ttl_val AS avg_ttl,
sqrt(ttl_variance_val) AS ttl_std,
IF(count_correlated_val > 0, count_no_wscale_val / count_correlated_val, 0) AS no_window_scale_ratio,
count_no_accept_enc_val / (hits + 1) AS missing_accept_enc_ratio,
count_http_scheme_val / (hits + 1) AS http_scheme_ratio,
-- P1 : nouvelles features de détection
IF(a.count_xff_val > 0, 1, 0) AS has_xff,
a.count_unusual_ct_val / greatest(a.count_post, 1) AS unusual_content_type_ratio,
a.count_non_std_port_val / (a.hits + 1) AS non_standard_port_ratio,
a.count_login_post_val / greatest(a.count_post, 1) AS login_post_concentration,
h.sec_ch_mobile_mismatch AS sec_ch_mobile_mismatch,
IF(count_xff_val > 0, 1, 0) AS has_xff,
count_unusual_ct_val / greatest(count_post, 1) AS unusual_content_type_ratio,
count_non_std_port_val / (hits + 1) AS non_standard_port_ratio,
count_login_post_val / greatest(count_post, 1) AS login_post_concentration,
sec_ch_mobile_mismatch AS sec_ch_mobile_mismatch,
-- §2 — Features HTTP/2 (fingerprint SETTINGS, cohérence H2↔JA4, pseudo-headers)
-- h2_settings_known : le fingerprint H2 est dans dict_browser_h2
IF(
COALESCE(h2.h2_fp, '') != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family',
tuple(COALESCE(h2.h2_fp, '')), '') != '',
h2_fp != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family', tuple(h2_fp), '') != '',
1, 0
) AS h2_settings_known,
-- h2_pseudo_order_match : l'ordre des pseudo-headers correspond à la famille JA4 déclarée
CASE
WHEN COALESCE(h2.h2_pseudo_ord, '') = '' THEN 0
WHEN h2_pseudo_ord = '' THEN 0
WHEN dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family',
tuple(a.ja4), '') IN ('Chromium', 'Chrome', 'Edge', 'Safari')
AND h2.h2_pseudo_ord = 'm,a,s,p' THEN 1
tuple(ja4), '') IN ('Chromium', 'Chrome', 'Edge', 'Safari')
AND h2_pseudo_ord = 'm,a,s,p' THEN 1
WHEN dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family',
tuple(a.ja4), '') = 'Firefox'
AND h2.h2_pseudo_ord = 'm,p,s,a' THEN 1
tuple(ja4), '') = 'Firefox'
AND h2_pseudo_ord = 'm,p,s,a' THEN 1
ELSE 0
END AS h2_pseudo_order_match,
-- h2_ja4_coherence : la famille navigateur H2 correspond à la famille JA4
IF(
COALESCE(h2.h2_fp, '') != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family',
tuple(COALESCE(h2.h2_fp, '')), '') =
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family',
tuple(a.ja4), '') AND
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family',
tuple(a.ja4), '') != '',
h2_fp != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family', tuple(h2_fp), '') =
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(ja4), '') AND
dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(ja4), '') != '',
1, 0
) AS h2_ja4_coherence,
-- h2_settings_rare : fingerprint H2 non reconnu (potentiellement suspect)
IF(
COALESCE(h2.h2_fp, '') != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family',
tuple(COALESCE(h2.h2_fp, '')), '') = '',
h2_fp != '' AND
dictGetOrDefault('ja4_processing.dict_browser_h2', 'browser_family', tuple(h2_fp), '') = '',
1, 0
) AS h2_settings_rare
FROM (
-- Jointure unique avec aliases explicites (contournement bug scope ClickHouse 24.8
-- où PARTITION BY src_ip échoue quand plusieurs sources de JOIN exposent src_ip)
SELECT
window_start, src_ip, ja4, host, src_asn,
any(src_country_code) AS src_country_code, any(src_as_name) AS src_as_name,
any(src_org) AS src_org, any(src_domain) AS src_domain, any(first_ua) AS first_ua,
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_fp_raw) AS tcp_fingerprint, varPopMerge(tcp_jitter_variance) AS tcp_jitter_variance,
varPopMerge(total_ip_length_var) AS request_size_variance,
any(tcp_win_raw * exp2(tcp_scale_raw)) AS true_window_size,
IF(any(tcp_mss_raw) > 0, any(tcp_win_raw) / any(tcp_mss_raw), 0) AS window_mss_ratio,
any(http_ver_raw) AS http_version, any(tls_alpn_raw) AS tls_alpn, any(tls_sni_raw) AS tls_sni,
max(correlated_raw) AS correlated, uniqMerge(unique_src_ports) AS unique_src_ports,
uniqMerge(unique_conn_id) AS unique_conn_id, max(max_keepalives) AS max_keepalives,
sum(orphan_count) AS orphan_count, sum(ip_id_zero_count) AS ip_id_zero_count,
sum(mss_1460_count) AS mss_1460_count,
sum(count_assets) AS count_assets, sum(count_no_referer) AS count_no_referer,
uniqMerge(uniq_ua) AS unique_ua,
varPopMerge(url_depth_variance) AS url_depth_variance,
sum(count_anomalous_payload) AS count_anomalous_payload,
uniqMerge(uniq_ja3) AS uniq_ja3_val,
avgMerge(avg_syn_ms) AS avg_syn_ms_val,
sum(tls12_count) AS tls12_count,
sum(count_head) AS count_head,
sum(count_no_sec_fetch) AS count_no_sec_fetch,
sum(count_generic_accept) AS count_generic_accept,
sum(count_http10) AS count_http10,
varPopMerge(ip_df_var) AS ip_df_variance,
avgIfMerge(avg_ttl) AS avg_ttl_val,
varPopIfMerge(ttl_var) AS ttl_variance_val,
sum(count_no_wscale) AS count_no_wscale_val,
sum(count_correlated) AS count_correlated_val,
sum(count_no_accept_enc) AS count_no_accept_enc_val,
sum(count_http_scheme) AS count_http_scheme_val,
-- P1 : nouvelles features de détection
sum(count_xff) AS count_xff_val,
sum(count_unusual_ct) AS count_unusual_ct_val,
sum(count_non_std_port) AS count_non_std_port_val,
sum(count_login_post) AS count_login_post_val
FROM ja4_processing.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 24 HOUR
GROUP BY window_start, src_ip, ja4, host, src_asn
) 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, max(has_sec_ch_ua) AS has_sec_ch_ua,
max(ua_ch_mismatch) AS ua_ch_mismatch,
max(sec_ch_mobile_mismatch) AS sec_ch_mobile_mismatch,
any(sec_fetch_mode) AS sec_fetch_mode, any(sec_fetch_dest) AS sec_fetch_dest
FROM ja4_processing.agg_header_fingerprint_1h
WHERE window_start >= now() - INTERVAL 24 HOUR
GROUP BY window_start, src_ip
) h ON a.src_ip = h.src_ip AND a.window_start = h.window_start
LEFT JOIN h2_agg h2 ON h2.src_ip = a.src_ip AND h2.window_start = a.window_start
a.window_start AS window_start,
a.src_ip AS src_ip,
a.ja4 AS ja4,
a.host AS host,
a.src_asn AS src_asn,
a.src_country_code AS src_country_code,
a.src_as_name AS src_as_name,
a.src_org AS src_org,
a.src_domain AS src_domain,
a.first_ua AS first_ua,
a.hits AS hits,
a.uniq_paths AS uniq_paths,
a.uniq_query_params AS uniq_query_params,
a.count_post AS count_post,
a.first_seen AS first_seen,
a.last_seen AS last_seen,
a.tcp_fingerprint AS tcp_fingerprint,
a.tcp_jitter_variance AS tcp_jitter_variance,
a.request_size_variance AS request_size_variance,
a.true_window_size AS true_window_size,
a.window_mss_ratio AS window_mss_ratio,
a.http_version AS http_version,
a.tls_alpn AS tls_alpn,
a.tls_sni AS tls_sni,
a.correlated AS correlated,
a.unique_src_ports AS unique_src_ports,
a.unique_conn_id AS unique_conn_id,
a.max_keepalives AS max_keepalives,
a.orphan_count AS orphan_count,
a.ip_id_zero_count AS ip_id_zero_count,
a.mss_1460_count AS mss_1460_count,
a.count_assets AS count_assets,
a.count_no_referer AS count_no_referer,
a.unique_ua AS unique_ua,
a.url_depth_variance AS url_depth_variance,
a.count_anomalous_payload AS count_anomalous_payload,
a.uniq_ja3_val AS uniq_ja3_val,
a.avg_syn_ms_val AS avg_syn_ms_val,
a.tls12_count AS tls12_count,
a.count_head AS count_head,
a.count_no_sec_fetch AS count_no_sec_fetch,
a.count_generic_accept AS count_generic_accept,
a.count_http10 AS count_http10,
a.ip_df_variance AS ip_df_variance,
a.avg_ttl_val AS avg_ttl_val,
a.ttl_variance_val AS ttl_variance_val,
a.count_no_wscale_val AS count_no_wscale_val,
a.count_correlated_val AS count_correlated_val,
a.count_no_accept_enc_val AS count_no_accept_enc_val,
a.count_http_scheme_val AS count_http_scheme_val,
a.count_xff_val AS count_xff_val,
a.count_unusual_ct_val AS count_unusual_ct_val,
a.count_non_std_port_val AS count_non_std_port_val,
a.count_login_post_val AS count_login_post_val,
-- colonnes de agg_header_fingerprint_1h
h.header_order_hash AS header_order_hash,
h.header_count AS header_count,
h.has_accept_language AS has_accept_language,
h.has_cookie AS has_cookie,
h.has_referer AS has_referer,
h.modern_browser_score AS modern_browser_score,
h.has_sec_ch_ua AS has_sec_ch_ua,
h.ua_ch_mismatch AS ua_ch_mismatch,
h.sec_ch_mobile_mismatch AS sec_ch_mobile_mismatch,
h.sec_fetch_mode AS sec_fetch_mode,
h.sec_fetch_dest AS sec_fetch_dest,
-- colonnes HTTP/2 (defaut vide si pas de trafic H2)
COALESCE(h2.h2_fp, '') AS h2_fp,
COALESCE(h2.h2_pseudo_ord, '') AS h2_pseudo_ord
FROM (
SELECT
window_start, src_ip, ja4, host, src_asn,
any(src_country_code) AS src_country_code, any(src_as_name) AS src_as_name,
any(src_org) AS src_org, any(src_domain) AS src_domain, any(first_ua) AS first_ua,
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_fp_raw) AS tcp_fingerprint, varPopMerge(tcp_jitter_variance) AS tcp_jitter_variance,
varPopMerge(total_ip_length_var) AS request_size_variance,
any(tcp_win_raw * exp2(tcp_scale_raw)) AS true_window_size,
IF(any(tcp_mss_raw) > 0, any(tcp_win_raw) / any(tcp_mss_raw), 0) AS window_mss_ratio,
any(http_ver_raw) AS http_version, any(tls_alpn_raw) AS tls_alpn, any(tls_sni_raw) AS tls_sni,
max(correlated_raw) AS correlated, uniqMerge(unique_src_ports) AS unique_src_ports,
uniqMerge(unique_conn_id) AS unique_conn_id, max(max_keepalives) AS max_keepalives,
sum(orphan_count) AS orphan_count, sum(ip_id_zero_count) AS ip_id_zero_count,
sum(mss_1460_count) AS mss_1460_count,
sum(count_assets) AS count_assets, sum(count_no_referer) AS count_no_referer,
uniqMerge(uniq_ua) AS unique_ua,
varPopMerge(url_depth_variance) AS url_depth_variance,
sum(count_anomalous_payload) AS count_anomalous_payload,
uniqMerge(uniq_ja3) AS uniq_ja3_val,
avgMerge(avg_syn_ms) AS avg_syn_ms_val,
sum(tls12_count) AS tls12_count,
sum(count_head) AS count_head,
sum(count_no_sec_fetch) AS count_no_sec_fetch,
sum(count_generic_accept) AS count_generic_accept,
sum(count_http10) AS count_http10,
varPopMerge(ip_df_var) AS ip_df_variance,
avgIfMerge(avg_ttl) AS avg_ttl_val,
varPopIfMerge(ttl_var) AS ttl_variance_val,
sum(count_no_wscale) AS count_no_wscale_val,
sum(count_correlated) AS count_correlated_val,
sum(count_no_accept_enc) AS count_no_accept_enc_val,
sum(count_http_scheme) AS count_http_scheme_val,
-- P1 : nouvelles features de détection
sum(count_xff) AS count_xff_val,
sum(count_unusual_ct) AS count_unusual_ct_val,
sum(count_non_std_port) AS count_non_std_port_val,
sum(count_login_post) AS count_login_post_val
FROM ja4_processing.agg_host_ip_ja4_1h
WHERE window_start >= now() - INTERVAL 24 HOUR
GROUP BY window_start, src_ip, ja4, host, src_asn
) 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, max(has_sec_ch_ua) AS has_sec_ch_ua,
max(ua_ch_mismatch) AS ua_ch_mismatch,
max(sec_ch_mobile_mismatch) AS sec_ch_mobile_mismatch,
any(sec_fetch_mode) AS sec_fetch_mode, any(sec_fetch_dest) AS sec_fetch_dest
FROM ja4_processing.agg_header_fingerprint_1h
WHERE window_start >= now() - INTERVAL 24 HOUR
GROUP BY window_start, src_ip
) h ON a.src_ip = h.src_ip AND a.window_start = h.window_start
-- §2 — LEFT JOIN fingerprints HTTP/2 depuis ja4_logs.http_logs
LEFT JOIN (
SELECT
toStartOfHour(time) AS h2_window,
toIPv6(src_ip) AS h2_ip,
anyIf(h2_fingerprint, h2_fingerprint != '') AS h2_fp,
anyIf(h2_pseudo_order, h2_pseudo_order != '') AS h2_pseudo_ord
FROM ja4_logs.http_logs
WHERE time >= now() - INTERVAL 24 HOUR
AND (h2_fingerprint != '' OR h2_pseudo_order != '')
GROUP BY toStartOfHour(time), toIPv6(src_ip)
) h2 ON h2.h2_ip = a.src_ip AND h2.h2_window = a.window_start
)
)
SELECT
*,
-(sum((hits / (total_ip_hits + 1)) * log2((hits / (total_ip_hits + 1)) + 0.000001)) OVER (PARTITION BY src_ip)) AS temporal_entropy,
sum(uniq_ja3_per_row) OVER (PARTITION BY src_ip) / greatest(distinct_ja4_count, 1) AS ja3_diversity_ratio,
-- §3 — Score de cohérence de fingerprint cross-layer [0.0, 1.0]
-- Combine : famille navigateur connue, cohérence H2↔JA4, cohérence TLS,
-- présence Accept-Language, et absence de mismatch UA/CH.
toFloat32(
CASE WHEN browser_family != '' THEN 0.25 ELSE 0.0 END
+ COALESCE(h2_ja4_coherence, 0) * 0.20