KQL Search

// 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 _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 =
        OfficeActivity
        | where ingestion_time() between (table_start .. table_end)
        // Filter events that may contain indicators
        | where isnotempty(ModifiedProperties)
        //| where not(_IndicatorsPrefilterLength < 10000 and not(ModifiedProperties has_any (_IndicatorsPrefilter))) // valid TLD ~1500 , "has_any" limit 10000
        | extend Domains = todynamic(dynamic_to_json(extract_all(_DomainRegex, dynamic([1]), ModifiedProperties)))
        | 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
        | project-rename OfficeActivity_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, UserId
    | project
        OfficeActivity_TimeGenerated,
        Description, ActivityGroupNames, IndicatorId, ThreatType, DomainName, Url, ExpirationDateTime, ConfidenceScore, AdditionalInformation,
        OfficeWorkload, RecordType, Operation, UserType, UserId, ClientIP, ResultStatus, OfficeObjectId, Parameters
};
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(OfficeActivity_TimeGenerated, *) by IndicatorId, UserId
| extend
    timestamp = OfficeActivity_TimeGenerated,
    AccountCustomEntity = UserId,
    IPCustomEntity = ClientIP,
    URLCustomEntity = Url