ja4-platform/shared/clickhouse/07_ai_features_view.sql

-- =============================================================================
-- 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.
-- =============================================================================

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,
        -- 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), ''), ''),
            ''
        ) 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), ''), ''),
            ''
        ) 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), ''), ''),
            ''
        ) 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,
        -- 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
    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
)
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;