-- ============================================================================ -- ARCHITECTURE DE DÉTECTION INTÉGRALE (v14 - corrections structurelles) -- Base : ja4_processing | Fenêtre : 24h | Dédoublonnage par src_ip -- v11 : ajout campaign_id, raw_anomaly_score dans ml_detected_anomalies -- v12 : ajout table ml_all_scores (toutes les classifications, sans seuil) -- v13 : partition + TTL sur agg_host_ip_ja4_1h et agg_header_fingerprint_1h -- v14 : correction ORDER BY ml_detected_anomalies (était (src_ip) → multi-colonnes) -- suppression colonne morte max_requests_per_sec -- rétention ml_all_scores portée à 7 jours -- partition + ttl_only_drop_parts sur ml_detected_anomalies et ml_all_scores -- filtre 7 jours sur view_ip_recurrence -- suppression vues dashboard inutilisées (summary/timeseries/threat_dist/variability) -- ajout views manquantes : view_dashboard_entities, view_dashboard_user_agents, -- view_ai_features_24h -- ============================================================================ -- 1. NETTOYAGE COMPLET DROP TABLE IF EXISTS ja4_processing.ml_all_scores; DROP DICTIONARY IF EXISTS ja4_processing.dict_bot_ip; DROP DICTIONARY IF EXISTS ja4_processing.dict_bot_ja4; DROP DICTIONARY IF EXISTS ja4_processing.dict_browser_ja4; DROP DICTIONARY IF EXISTS ja4_processing.dict_asn_reputation; DROP TABLE IF EXISTS ja4_processing.ml_detected_anomalies; DROP VIEW IF EXISTS ja4_processing.view_ip_recurrence; DROP VIEW IF EXISTS ja4_processing.view_ai_features_1h; DROP VIEW IF EXISTS ja4_processing.view_ai_features_24h; -- Vues dashboard inutilisées (non référencées par les routes Python) DROP VIEW IF EXISTS ja4_processing.view_dashboard_summary; DROP VIEW IF EXISTS ja4_processing.view_dashboard_timeseries; DROP VIEW IF EXISTS ja4_processing.view_dashboard_threat_dist; DROP VIEW IF EXISTS ja4_processing.view_dashboard_variability; -- Vues dashboard manquantes (recréées plus bas) DROP VIEW IF EXISTS ja4_processing.view_dashboard_entities; DROP VIEW IF EXISTS ja4_processing.view_dashboard_user_agents; -- Suppression des anciennes vues heuristiques DROP VIEW IF EXISTS ja4_processing.view_host_ip_ja4_rotation; DROP VIEW IF EXISTS ja4_processing.view_host_ja4_anomalies; DROP VIEW IF EXISTS ja4_processing.view_form_bruteforce_detected; DROP VIEW IF EXISTS ja4_processing.view_alpn_mismatch_detected; DROP VIEW IF EXISTS ja4_processing.view_tcp_spoofing_detected; DROP VIEW IF EXISTS ja4_processing.mv_agg_host_ip_ja4_1h; DROP TABLE IF EXISTS ja4_processing.agg_host_ip_ja4_1h; DROP VIEW IF EXISTS ja4_processing.mv_agg_header_fingerprint_1h; DROP TABLE IF EXISTS ja4_processing.agg_header_fingerprint_1h; -- ============================================================================ -- 2. DICTIONNAIRES DE RÉPUTATION EN RAM -- ============================================================================ CREATE DICTIONARY ja4_processing.dict_bot_ip (prefix String, bot_name String) PRIMARY KEY prefix SOURCE(FILE(path '/var/lib/clickhouse/user_files/bot_ip.csv' format 'CSV')) LAYOUT(IP_TRIE()) LIFETIME(MIN 300 MAX 300); CREATE DICTIONARY ja4_processing.dict_bot_ja4 (ja4 String, bot_name String) PRIMARY KEY ja4 SOURCE(FILE(path '/var/lib/clickhouse/user_files/bot_ja4.csv' format 'CSV')) LAYOUT(COMPLEX_KEY_HASHED()) LIFETIME(MIN 300 MAX 300); CREATE DICTIONARY ja4_processing.dict_asn_reputation (src_asn UInt64, label String) PRIMARY KEY src_asn SOURCE(FILE(path '/var/lib/clickhouse/user_files/asn_reputation.csv' format 'CSV')) LAYOUT(HASHED()) LIFETIME(MIN 300 MAX 300); CREATE DICTIONARY ja4_processing.dict_browser_ja4 (ja4 String, browser_family String, tls_library String, context String) PRIMARY KEY ja4 SOURCE(FILE(path '/var/lib/clickhouse/user_files/browser_ja4.csv' format 'CSV')) LAYOUT(COMPLEX_KEY_HASHED()) LIFETIME(MIN 300 MAX 300); -- ============================================================================ -- 3. TABLE D'AGRÉGATION COMPORTEMENTALE (L4 / L5 / L7) -- ============================================================================ CREATE TABLE ja4_processing.agg_host_ip_ja4_1h ( window_start DateTime, src_ip IPv6, ja4 String, host String, src_asn UInt32, src_country_code SimpleAggregateFunction(any, String), src_as_name SimpleAggregateFunction(any, String), src_org SimpleAggregateFunction(any, String), src_domain SimpleAggregateFunction(any, 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), tcp_fp_raw SimpleAggregateFunction(any, String), tcp_jitter_variance AggregateFunction(varPop, Float64), tcp_win_raw SimpleAggregateFunction(any, UInt32), tcp_scale_raw SimpleAggregateFunction(any, UInt32), tcp_mss_raw SimpleAggregateFunction(any, UInt32), tcp_ttl_raw SimpleAggregateFunction(any, UInt32), http_ver_raw SimpleAggregateFunction(any, String), tls_alpn_raw SimpleAggregateFunction(any, String), tls_sni_raw SimpleAggregateFunction(any, String), first_ua SimpleAggregateFunction(any, String), correlated_raw SimpleAggregateFunction(max, UInt8), unique_src_ports AggregateFunction(uniq, UInt16), unique_conn_id AggregateFunction(uniq, String), max_keepalives SimpleAggregateFunction(max, UInt32), orphan_count SimpleAggregateFunction(sum, UInt64), ip_id_zero_count SimpleAggregateFunction(sum, UInt64), total_ip_length_var AggregateFunction(varPop, Float64), mss_1460_count SimpleAggregateFunction(sum, UInt64), count_assets SimpleAggregateFunction(sum, UInt64), count_no_referer SimpleAggregateFunction(sum, UInt64), uniq_ua AggregateFunction(uniq, String), max_requests_per_sec SimpleAggregateFunction(max, UInt32), -- DEPRECATED: toujours 0, conservé pour compatibilité url_depth_variance AggregateFunction(varPop, Float64), count_anomalous_payload SimpleAggregateFunction(sum, UInt64), -- B features (ajoutées v14) uniq_ja3 AggregateFunction(uniq, String), -- B1: diversité JA3/JA4 avg_syn_ms AggregateFunction(avg, Float64), -- B2: SYN timing moyen (pour CV) tls12_count SimpleAggregateFunction(sum, UInt64), -- B3: ratio TLS 1.2 count_head SimpleAggregateFunction(sum, UInt64), -- B4: ratio requêtes HEAD count_no_sec_fetch SimpleAggregateFunction(sum, UInt64),-- B5: absence Sec-Fetch-* count_generic_accept SimpleAggregateFunction(sum, UInt64),-- B6: Accept générique count_http10 SimpleAggregateFunction(sum, UInt64), -- B7: ratio HTTP/1.0 ip_df_var AggregateFunction(varPop, Float64) -- B8: variance bit DF ) ENGINE = AggregatingMergeTree() PARTITION BY toDate(window_start) ORDER BY (window_start, src_ip, ja4, host) TTL window_start + INTERVAL 7 DAY SETTINGS index_granularity = 8192, ttl_only_drop_parts = 1; -- ============================================================================ -- 4. VUE MATÉRIALISÉE → agg_host_ip_ja4_1h -- ============================================================================ CREATE MATERIALIZED VIEW ja4_processing.mv_agg_host_ip_ja4_1h TO ja4_processing.agg_host_ip_ja4_1h AS SELECT toStartOfHour(src.time) AS window_start, toIPv6(src.src_ip) AS src_ip, src.ja4, src.host, src.src_asn, any(src.src_country_code) AS src_country_code, any(src.src_as_name) AS src_as_name, any(src.src_org) AS src_org, any(src.src_domain) AS src_domain, 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(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_fp_raw, varPopState(toFloat64(src.syn_to_clienthello_ms)) AS tcp_jitter_variance, any(src.tcp_meta_window_size) AS tcp_win_raw, any(src.tcp_meta_window_scale) AS tcp_scale_raw, any(src.tcp_meta_mss) AS tcp_mss_raw, any(src.ip_meta_ttl) AS tcp_ttl_raw, any(src.http_version) AS http_ver_raw, any(src.tls_alpn) AS tls_alpn_raw, any(src.tls_sni) AS tls_sni_raw, any(src.header_user_agent) AS first_ua, max(toUInt8(src.correlated)) AS correlated_raw, uniqState(toUInt16(src.src_port)) AS unique_src_ports, uniqState(src.conn_id) AS unique_conn_id, max(toUInt32(src.keepalives)) AS max_keepalives, sum(IF(src.orphan_side = 'A' OR src.correlated = 0, 1, 0)) AS orphan_count, sum(IF(src.ip_meta_id == 0, 1, 0)) AS ip_id_zero_count, varPopState(toFloat64(src.ip_meta_total_length)) AS total_ip_length_var, sum(IF(src.tcp_meta_mss == 1460, 1, 0)) AS mss_1460_count, sum(IF(match(src.path, '(?i)\.(png|jpg|jpeg|gif|css|js|ico|woff2|svg|eot)$'), 1, 0)) AS count_assets, sum(IF(position(src.client_headers, 'Referer') = 0, 1, 0)) AS count_no_referer, uniqState(src.header_user_agent) AS uniq_ua, 0 AS max_requests_per_sec, varPopState(toFloat64(length(replaceAll(src.path, '/', '//')) - length(src.path))) AS url_depth_variance, sum(IF(src.ip_meta_total_length < 60 OR src.ip_meta_total_length > 1500, 1, 0)) AS count_anomalous_payload, -- B features uniqState(src.ja3) AS uniq_ja3, avgState(toFloat64(src.syn_to_clienthello_ms)) AS avg_syn_ms, sum(IF(src.tls_version = '1.2', 1, 0)) AS tls12_count, sum(IF(src.method = 'HEAD', 1, 0)) AS count_head, sum(IF(length(src.header_sec_fetch_site) = 0, 1, 0)) AS count_no_sec_fetch, sum(IF(length(src.header_accept) < 5, 1, 0)) AS count_generic_accept, sum(IF(src.http_version = 'HTTP/1.0', 1, 0)) AS count_http10, varPopState(toFloat64(src.ip_meta_df)) AS ip_df_var FROM ja4_logs.http_logs AS src GROUP BY window_start, src_ip, ja4, host, src_asn; -- ============================================================================ -- 5. TABLE D'AGRÉGATION DES HEADERS (L7) -- ============================================================================ CREATE TABLE ja4_processing.agg_header_fingerprint_1h ( window_start DateTime, src_ip IPv6, 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), modern_browser_score SimpleAggregateFunction(max, UInt8), has_sec_ch_ua SimpleAggregateFunction(max, UInt8), ua_ch_mismatch SimpleAggregateFunction(max, UInt8), sec_fetch_mode SimpleAggregateFunction(any, String), sec_fetch_dest SimpleAggregateFunction(any, String) ) ENGINE = AggregatingMergeTree() PARTITION BY toDate(window_start) ORDER BY (window_start, src_ip) TTL window_start + INTERVAL 7 DAY SETTINGS index_granularity = 8192, ttl_only_drop_parts = 1; CREATE MATERIALIZED VIEW ja4_processing.mv_agg_header_fingerprint_1h TO ja4_processing.agg_header_fingerprint_1h AS SELECT toStartOfHour(src.time) AS window_start, toIPv6(src.src_ip) AS 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, max(toUInt8(if(length(src.header_sec_ch_ua) > 0, 100, if(length(src.header_sec_fetch_site) > 0, 70, 0)))) AS modern_browser_score, max(toUInt8(if(length(src.header_sec_ch_ua) > 0, 1, 0))) AS has_sec_ch_ua, max(toUInt8(if((position(src.header_user_agent, 'Windows') > 0 AND position(src.header_sec_ch_ua_platform, 'Windows') == 0) OR (position(src.header_user_agent, 'iPhone') > 0 AND position(src.header_sec_ch_ua_platform, 'iOS') == 0), 1, 0))) AS ua_ch_mismatch, any(src.header_sec_fetch_mode) AS sec_fetch_mode, any(src.header_sec_fetch_dest) AS sec_fetch_dest FROM ja4_logs.http_logs AS src GROUP BY window_start, src.src_ip; -- ============================================================================ -- 6. TABLE DE RÉSULTATS ML — MENACES UNIQUEMENT (scores < seuil) -- ============================================================================ CREATE TABLE ja4_processing.ml_detected_anomalies ( detected_at DateTime, src_ip IPv6, ja4 String, host String, bot_name String, anomaly_score Float32, threat_level String, model_name String, recurrence UInt32, asn_number String, asn_org String, asn_detail String, asn_domain String, country_code String, asn_label String, hits UInt64, hit_velocity Float32, fuzzing_index Float32, post_ratio Float32, 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, alpn_http_mismatch UInt8, is_alpn_missing UInt8, sni_host_mismatch UInt8, header_count UInt16, has_accept_language UInt8, has_cookie UInt8, has_referer UInt8, modern_browser_score UInt8, has_sec_ch_ua UInt8, is_headless UInt8, ua_ch_mismatch UInt8, header_order_shared_count UInt32, ip_id_zero_ratio Float32, request_size_variance Float32, multiplexing_efficiency Float32, mss_mobile_mismatch UInt8, correlated UInt8, reason String, asset_ratio Float32, direct_access_ratio Float32, is_ua_rotating UInt8, distinct_ja4_count UInt32, src_port_density Float32, ja4_asn_concentration Float32, ja4_country_concentration Float32, is_rare_ja4 UInt8, header_order_confidence Float32, distinct_header_orders UInt32, temporal_entropy Float32, path_diversity_ratio Float32, url_depth_variance Float32, anomalous_payload_ratio Float32, -- Colonnes ajoutées en v11 (bot_detector v11) campaign_id Int32 DEFAULT -1, raw_anomaly_score Float32 DEFAULT 0 ) ENGINE = ReplacingMergeTree(detected_at) PARTITION BY toDate(detected_at) ORDER BY (src_ip, ja4, host, model_name) TTL detected_at + INTERVAL 7 DAY SETTINGS index_granularity = 8192, ttl_only_drop_parts = 1; -- ============================================================================ -- 6b. TABLE DE TOUTES LES CLASSIFICATIONS (sans seuil, pour observabilité) -- ============================================================================ CREATE TABLE ja4_processing.ml_all_scores ( detected_at DateTime, window_start DateTime, src_ip IPv6, ja4 String, host String, bot_name String, anomaly_score Float32, raw_anomaly_score Float32, threat_level String, model_name String, correlated UInt8, asn_number String, asn_org String, country_code String, asn_label String, hits UInt64, hit_velocity Float32, fuzzing_index Float32, post_ratio Float32, campaign_id Int32 ) ENGINE = ReplacingMergeTree(detected_at) PARTITION BY toDate(window_start) ORDER BY (window_start, src_ip, ja4, host, model_name) TTL window_start + INTERVAL 7 DAY SETTINGS index_granularity = 8192, ttl_only_drop_parts = 1; -- ============================================================================ -- 7. VUE DE RÉCURRENCE -- ============================================================================ CREATE OR REPLACE VIEW ja4_processing.view_ip_recurrence AS SELECT src_ip, count() AS recurrence, min(detected_at) AS first_seen, max(detected_at) AS last_seen, min(anomaly_score) AS worst_score, argMin(threat_level, anomaly_score) AS worst_threat_level FROM ja4_processing.ml_detected_anomalies WHERE detected_at >= now() - INTERVAL 7 DAY GROUP BY src_ip; -- ============================================================================ -- 8. VUE IA PRINCIPALE (Avec CTE pour Entropie Temporelle) -- ============================================================================ CREATE OR REPLACE VIEW ja4_processing.view_ai_features_1h AS WITH 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, 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), ''), ''), '' ) AS bot_name, dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(a.ja4), '') AS browser_family, 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, -- B features : TLS/TCP (disponibles correlated=1 uniquement) 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, -- B2 a.tls12_count / (a.hits + 1) AS tls12_ratio, -- B3 -- B features : HTTP pures (disponibles correlated=0 et 1) a.count_head / (a.hits + 1) AS head_ratio, -- B4 a.count_no_sec_fetch / (a.hits + 1) AS sec_fetch_absence_rate, -- B5 a.count_generic_accept / (a.hits + 1) AS generic_accept_ratio, -- B6 a.count_http10 / (a.hits + 1) AS http10_ratio, -- B7 a.ip_df_variance AS ip_df_variance -- B8 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, -- B feature aggregates 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 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, 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 ) SELECT *, -(sum((hits / (total_ip_hits + 1)) * log2((hits / (total_ip_hits + 1)) + 0.000001)) OVER (PARTITION BY src_ip)) AS temporal_entropy, -- B1: ratio diversité JA3/JA4 par src_ip (signal: bots avec JA3 rotatifs sur peu de JA4) sum(uniq_ja3_per_row) OVER (PARTITION BY src_ip) / greatest(distinct_ja4_count, 1) AS ja3_diversity_ratio FROM base_data; -- ============================================================================ -- VUES POUR LE DASHBOARD WEB -- ============================================================================ -- Vue entités : données brutes par IP/JA4 pour clustering et incidents -- Colonnes utilisées : entity_type, entity_value, user_agents, client_headers, src_ip, ja4, log_date CREATE OR REPLACE VIEW ja4_processing.view_dashboard_entities AS SELECT 'ip' AS entity_type, toString(src_ip) AS entity_value, src_ip, ja4, log_date, groupUniqArray(100)(header_user_agent) AS user_agents, splitByChar(',', any(client_headers)) AS client_headers FROM ja4_logs.http_logs WHERE log_date >= today() - 7 AND header_user_agent != '' GROUP BY src_ip, ja4, log_date; -- Vue user-agents agrégés par heure pour les routes fingerprints/metrics -- Colonnes utilisées : src_ip, ja4, hour, log_date, user_agents (Array), requests CREATE OR REPLACE VIEW ja4_processing.view_dashboard_user_agents AS SELECT src_ip, ja4, toStartOfHour(time) AS hour, log_date, groupUniqArray(50)(header_user_agent) AS user_agents, count() AS requests FROM ja4_logs.http_logs WHERE log_date >= today() - 7 AND header_user_agent != '' GROUP BY src_ip, ja4, hour, log_date; -- ============================================================================ -- VUE IA 24H (fenêtre glissante journalière — détection d'attaquants lents) -- Même structure que view_ai_features_1h mais agrège toutes les fenêtres horaires -- en une seule ligne par (src_ip, ja4, host) sur 24h. -- Utilisée par bot_detector en mode ENABLE_MULTIWINDOW=true. -- ============================================================================ CREATE OR REPLACE VIEW ja4_processing.view_ai_features_24h AS WITH base_data AS ( SELECT toStartOfDay(a.first_seen) AS 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, 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), ''), ''), '' ) AS bot_name, dictGetOrDefault('ja4_processing.dict_browser_ja4', 'browser_family', tuple(a.ja4), '') AS browser_family, 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 FROM ( SELECT 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 FROM ja4_processing.agg_host_ip_ja4_1h WHERE window_start >= now() - INTERVAL 24 HOUR GROUP BY src_ip, ja4, host, src_asn ) a LEFT JOIN ( SELECT 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, 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 src_ip ) h ON a.src_ip = h.src_ip ) 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 FROM base_data;