Query Details

Multiple Domain Entity Security Alert

Query

// This query assumes a feed of threat indicators is ingested/synchronized periodically, and each synchronization ingests new indicators and only old indicators that have been modified.
// Active threat indicators in Sentinel are renovated as ThreatIntelligenceIndicator events every ~12 days.
let query_frequency = 1h;
let query_period = 14d;
let query_wait = 0h;
let table_query_lookback = 14d;
let _TIBenignProperty =
    _GetWatchlist('ID-TIBenignProperty')
    | where Notes has_any ("[SourceDomain]", "[DestinationDomain]")
    | project IndicatorId, BenignProperty
;
let _TIExcludedSources = toscalar(
    _GetWatchlist('Activity-ExpectedSignificantActivity')
    | where Activity == "ThreatIndicatorSource"
    | summarize make_list(Auxiliar)
    );
let _ExcludedAlerts =
    _GetWatchlist('AlertName-MonitoredDetections')
    | where Notes has "[ExcludedTIAlerts]"
    | project ProductName, AlertName, AnalyticsId = tostring(AnalyticsId)
;
let _DomainRegex = toscalar(
    _GetWatchlist('RegEx-SingleRegularExpressions')
    | where UseCase == "Threat Intelligence Indicator Domain"
    | project RegEx
    );
let _TITableMatch = (table_start: datetime, table_end: datetime, only_new_ti: boolean, ti_start: datetime = datetime(null)) {
    // Scheduled Analytics rules have a query period limit of 14d
    let _Indicators =// materialize(
        ThreatIntelligenceIndicator
        | where TimeGenerated > ago(query_period)
        // Take the earliest TimeGenerated and the latest column info
        | summarize hint.strategy=shuffle
            minTimeGenerated = min(TimeGenerated),
            arg_max(TimeGenerated, Active, Description, ActivityGroupNames, IndicatorId, ThreatType, DomainName, Url, ExpirationDateTime, ConfidenceScore, AdditionalInformation, ExternalIndicatorId)
            by IndicatorId
        // Remove inactive or expired indicators
        | where not(not(Active) or ExpirationDateTime < now())
        // Pick indicators that contain the desired entity type
        | where isnotempty(DomainName)
        | extend Domain = tolower(DomainName)
        // Remove indicators from specific sources
        | where not(AdditionalInformation has_any (_TIExcludedSources) or Description has_any (_TIExcludedSources))
        // Remove excluded indicators with benign properties
        | join kind=leftanti _TIBenignProperty on IndicatorId, $left.Domain == $right.BenignProperty
        // Deduplicate indicators by Domain column, equivalent to using join kind=innerunique afterwards
        | summarize hint.strategy=shuffle
            minTimeGenerated = min(minTimeGenerated),
            take_any(*)
            by Domain
        // If we want only new indicators, remove indicators received previously
        | where not(only_new_ti and minTimeGenerated < ti_start)
    //)
    ;
    //let _IndicatorsLength = toscalar(_Indicators | summarize count());
    //let _IndicatorsPrefilter = toscalar(
    //    _Indicators
    //    | extend AuxiliarField = tostring(split(Domain, ".")[-1])
    //    | summarize make_set_if(AuxiliarField, isnotempty(AuxiliarField))
    //);
    //let _IndicatorsPrefilterLength = array_length(_IndicatorsPrefilter);
    let _TableEvents =
        SecurityAlert
        | where TimeGenerated between (table_start .. table_end)
        // Remove TI map alerts
        | extend MSTI = (VendorName == "Microsoft" and ProductName == 'Azure Sentinel' and (ProviderName == "Threat Intelligence Alerts" or AlertName has "TI map"))
        | where MSTI == false //or MSTI == true
        // Remove excluded alerts
        | extend AnalyticsId = iff(ProductName == "Azure Sentinel", tostring(split(AlertType, "_")[-1]), AlertType)
        | join kind=leftanti _ExcludedAlerts on ProductName, AlertName, AnalyticsId
        // Filter events that may contain indicators
        | where isnotempty(Entities)
        //| where not(_IndicatorsPrefilterLength < 10000 and not(Entities has_any (_IndicatorsPrefilter))) // valid TLD ~1500 , "has_any" limit 10000
        | extend Domains = todynamic(dynamic_to_json(extract_all(_DomainRegex, dynamic([1]), Entities)))
        | mv-expand Domain = Domains to typeof(string)
        | where isnotempty(Domain)
        | summarize hint.strategy=shuffle take_any(*) by OriginalDomain = Domain
        //| where not(_IndicatorsPrefilterLength < 10000 and not(tostring(split(OriginalDomain, ".")[-1]) in (_IndicatorsPrefilter)))
        | extend SplitLevelDomains = split(OriginalDomain, ".")
        | mv-expand Level = range(0, array_length(SplitLevelDomains) - 2) to typeof(int)
        | extend Domain = strcat_array(array_slice(SplitLevelDomains, Level, -1), ".")
        //| where not(_IndicatorsLength < 1000000 and not(Domain in (toscalar(_Indicators | summarize make_list(Domain))))) // "in" limit 1.000.000
        // Extract one entity of each type of multiple possible
        | mv-apply EntitiesDynamic = todynamic(Entities) on (
            summarize
                Alert_Account = take_anyif(strcat(tostring(EntitiesDynamic.Name), iff(isnotempty(tostring(EntitiesDynamic.UPNSuffix)), "@", ""), tostring(EntitiesDynamic.UPNSuffix)), EntitiesDynamic.Type == "account" and not(EntitiesDynamic.IsValid == "false")),
                Alert_HostName = take_anyif(tostring(EntitiesDynamic.HostName), EntitiesDynamic.Type == "host"),
                Alert_IPAddress = take_anyif(tostring(EntitiesDynamic.Address), EntitiesDynamic.Type == "ip")
            )
        | project-rename Alert_Description = Description
        | project-rename SecurityAlert_TimeGenerated = TimeGenerated
    ;
    _Indicators
    | join kind=inner hint.strategy=shuffle _TableEvents on Domain
    // Take only a single event by key columns
    //| summarize hint.strategy=shuffle take_any(*) by Domain, AlertName
    | project
        SecurityAlert_TimeGenerated,
        Description, ActivityGroupNames, IndicatorId, ThreatType, DomainName, Url, ExpirationDateTime, ConfidenceScore, AdditionalInformation,
        AlertName, AlertSeverity, Entities, ProviderName, ProductName, VendorName, AnalyticsId, Alert_Description, Alert_Account, Alert_IPAddress, Alert_HostName, CompromisedEntity
};
union// isfuzzy=true
    // Match      current table events                                all indicators available
    _TITableMatch(ago(query_frequency + query_wait), ago(query_wait), false),
    // Match      past table events                                                          new indicators since last query execution
    _TITableMatch(ago(table_query_lookback + query_wait), ago(query_frequency + query_wait), true, ago(query_frequency))
| summarize arg_max(SecurityAlert_TimeGenerated, *) by IndicatorId, AlertName
| extend
    timestamp = SecurityAlert_TimeGenerated,
    AccountCustomEntity = Alert_Account,
    IPCustomEntity = Alert_IPAddress,
    HostCustomEntity = Alert_HostName,
    URLCustomEntity = Url

Explanation

This KQL (Kusto Query Language) script is designed to analyze threat intelligence data and security alerts in Microsoft Sentinel. Here's a simplified breakdown of what the query does:

  1. Setup and Definitions:

    • It defines several parameters and helper functions to control the query's behavior, such as how often it runs (query_frequency), the period it covers (query_period), and the lookback period for table queries (table_query_lookback).
  2. Watchlists and Exclusions:

    • It retrieves and processes watchlists to identify benign properties, excluded sources, and excluded alerts. These are used to filter out non-threatening or irrelevant data.
  3. Domain Regex:

    • It fetches a regular expression pattern to identify domain names related to threat intelligence indicators.
  4. Threat Intelligence Indicators:

    • It extracts active threat intelligence indicators from the ThreatIntelligenceIndicator table, filtering out inactive or expired ones and those from excluded sources. It also ensures that only new indicators are considered if specified.
  5. Security Alerts:

    • It retrieves security alerts from the SecurityAlert table within a specified time range, excluding certain types of alerts and those from excluded sources. It extracts domain names from these alerts and matches them against the threat intelligence indicators.
  6. Matching and Joining:

    • It matches the extracted domains from security alerts with the threat intelligence indicators to find correlations. It joins these matches to provide a comprehensive view of the threat landscape.
  7. Result Compilation:

    • It combines current and past matches to provide a complete picture of threat intelligence indicators and related security alerts. The results are summarized to show the most recent alert for each indicator.
  8. Output:

    • The final output includes various details about the matched indicators and alerts, such as timestamps, descriptions, threat types, domain names, and associated entities like accounts, IP addresses, and hostnames.

In essence, this query helps identify and correlate threat intelligence indicators with security alerts, filtering out noise and focusing on relevant threats to provide actionable insights.

Details

Jose Sebastián Canós profile picture

Jose Sebastián Canós

Released: December 13, 2023

Tables

ThreatIntelligenceIndicatorSecurityAlert

Keywords

ThreatIntelligenceIndicatorSecurityAlertWatchlistDomainNameAlertNameVendorNameProductNameProviderNameAnalyticsIdEntitiesDynamicHostNameIPAddressAccountUPNSuffixAddress

Operators

lethas_anyprojecttoscalarwheresummarizemake_list

Actions

GitHub