Name:Geographic Improbable Location id:64f91df1-49ec-46aa-81bd-2282d3cea765 version:1 date:2025-06-03 author:Marissa Bower, Raven Tait status:experimental type:Anomaly Description:Geolocation data can be inaccurate or easily spoofed by Remote Employment Fraud (REF) workers. REF actors sometimes slip up and reveal their true location, creating what we call 'improbable travel' scenarios — logins from opposite sides of the world within minutes. This identifies situations where these travel scenarios occur. Data_source:
-Okta
search:| tstats summariesonly=true values(Authentication.app) as app from datamodel=Authentication.Authentication where (`okta` OR (index="firewall" AND sourcetype="pan:globalprotect")) AND Authentication.action="success" AND Authentication.app IN ("Workday", "Slack", "*GlobalProtect", "Jira*", "Atlassian Cloud", "Zoom") AND NOT Authentication.user="unknown" by _time index sourcetype host Authentication.user Authentication.src span=1s | `drop_dm_object_name("Authentication")` | fields user,src,app,_time,count,host | eval user=lower(replace(user, "((^.*\\\)|(@.*$))", "")) | join type=outer user [| inputlookup identity_lookup_expanded where user_status=active | rex field=email "^(?<user>[a-zA-Z0-9_\-\.]+)@([a-zA-Z0-9_\-\.]+)\.([a-zA-Z]{2,5})$" | rename email as user_email bunit as user_bunit priority as user_priority work_country as user_work_country work_city as user_work_city | fields user user_email user_bunit user_priority user_work_country user_work_city] | eventstats dc(src) as src_count by user | eventstats dc(user) as user_count by src | sort 0 + _time | iplocation src | lookup local=true asn_lookup_by_cidr ip as src OUTPUT ip asn description | eval session_lat=if(isnull(src_lat), lat, src_lat), session_lon=if(isnull(src_long), lon, src_long), session_city=if(isnull(src_city), City, src_city), session_country=if(isnull(src_country), Country, src_country), session_region=if(isnull(src_region), Region, src_region) | eval session_city=if(isnull(session_city) OR match(session_city,"^\s+|^$"), null(), session_city), session_country=if(isnull(session_country) OR match(session_country,"^\s+|^$"), null(), session_country), session_region=if(isnull(session_region) OR match(session_region,"^\s+|^$"), null(), session_region) | where isnotnull(session_lat) and isnotnull(session_lon) | eval session_city=if(isnull(session_city),"-",session_city), session_country=if(isnull(session_country),"-",session_country), session_region=if(isnull(session_region),"-",session_region) | streamstats current=t window=2 earliest(session_region) as prev_region,earliest(session_lat) as prev_lat, earliest(session_lon) as prev_lon, earliest(session_city) as prev_city, earliest(session_country) as prev_country, earliest(_time) as prev_time, earliest(src) as prev_src, latest(user_bunit) as user_bunit, earliest(app) as prev_app values(user_work_country) as user_work_country by user | where (src!=prev_src) AND !(prev_city=session_city AND prev_country=session_country) AND ((isnotnull(prev_city) AND isnotnull(session_city)) OR prev_country!=session_country) | `globedistance(session_lat,session_lon,prev_lat,prev_lon,"m")` | eval time_diff=if((_time-prev_time)==0, 1, _time - prev_time) | eval speed = round(distance*3600/time_diff,2) | eval distance= round(distance,2) | eval user_work_country=case(user_work_country="usa","United States", user_work_country="cze","Czechia", user_work_country="pol","Poland", user_work_country="ind","India", user_work_country="fra","France", user_work_country="can","Canada", user_work_country="mys","Malaysia", user_work_country="kor","South Korea", user_work_country="aus","Australia", user_work_country="bel","Belgium", user_work_country="dnk","Denmark", user_work_country="bra","Brazil", user_work_country="deu","Germany", user_work_country="jpn","Japan", user_work_country="che","Switzerland", user_work_country="swe","Sweden", user_work_country="zaf","South Africa", user_work_country="irl","Ireland", user_work_country="ita","Italy", user_work_country="nor","Norway", user_work_country="gbr","United Kingdom", user_work_country="hkg","Hong Kong", user_work_country="chn","China", user_work_country="esp","Spain", user_work_country="nld", "Netherlands", user_work_country="twn","Taiwan", user_work_country="est","Estonia", user_work_country="sgp","Singapore", user_work_country="are","United Arab Emirates", 1=1,"N/A") | lookup local=true asn_lookup_by_cidr ip as prev_src OUTPUT ip as prev_ip asn as prev_asn description as prev_description | eval suspect=if(!user_work_country==session_country,"Sketchy","Normal") | search (speed>500 AND distance>750) | table _time,prev_time,user,host,src,prev_src,app,prev_app,distance,speed,suspect,session_city,session_region, session_country,prev_city,prev_region,prev_country,user_priority,user_work_*,prev_ip,ip,asn,prev_asn,prev_description,description | rename _time as event_time | convert ctime(event_time) timeformat="%Y-%m-%d %H:%M:%S" | convert ctime(prev_time) timeformat="%Y-%m-%d %H:%M:%S" | eval problem=if(!session_country==prev_country AND (!session_country==user_work_country),"Yes","Nope") | search NOT (prev_city="-" OR session_city="-") AND NOT [inputlookup known_devices_public_ip_filter.csv | fields ip | rename ip as src] | dedup user host prev_src src | fillnull value="N/A" | search problem="Yes"| `geographic_improbable_location_filter`
how_to_implement:The analytic leverages Okta OktaIm2 logs to be ingested using the Splunk Add-on for Okta Identity Cloud (https://splunkbase.splunk.com/app/6553). This also utilizes Splunk Enterprise Security Suite for several macros and lookups. The known_devices_public_ip_filter lookup is a placeholder for known public edge devices in your network. known_false_positives:Legitimate usage of some VPNs may cause false positives. Tune as needed. References: drilldown_searches: name:'View the detection results for - "$user$"' search:'%original_detection_search% | search Authentication.user = "$user$"' earliest_offset:'$info_min_time$' latest_offset:'$info_max_time$' name:'View risk events for the last 7 days for - "$user$"' search:'| from datamodel Risk.All_Risk | search normalized_risk_object IN ("$user$") starthoursago=168 | stats count min(_time) as firstTime max(_time) as lastTime values(search_name) as "Search Name" values(risk_message) as "Risk Message" values(analyticstories) as "Analytic Stories" values(annotations._all) as "Annotations" values(annotations.mitre_attack.mitre_tactic) as "ATT&CK Tactics" by normalized_risk_object | `security_content_ctime(firstTime)` | `security_content_ctime(lastTime)`' earliest_offset:'$info_min_time$' latest_offset:'$info_max_time$' tags: analytic_story: - 'Remote Employment Fraud' asset_type:Identity mitre_attack_id: - 'T1078' product: - 'Splunk Enterprise' - 'Splunk Enterprise Security' - 'Splunk Cloud' security_domain:identity
