Account Takeover Detection

This dataset provides detailed records of account takeover incidents, capturing unauthorized access attempts, credential compromises, device and contact information changes, and abnormal transactions. It includes detection methods, response actions, and resolution status, enabling advanced security analytics, fraud detection, and incident response optimization.

  • opened 6 times
  • last updated 29 Oct 2025
  • by GoMask
The brief that made it

Automated detection and investigation of account takeover attempts

Sample rows

preview · 8 of 400 rows · all 21 columns
incident_idstringdetection_methodstringtransaction_amountfloatabnormal_transaction_detectedbooleangeo_location_countrystringuser_idstringusernamestringemailstringincident_datetimedatetimeincident_typestringdevice_idstringdevice_typestringip_addressstringgeo_location_citystringcontact_info_changedbooleandevice_changedbooleantransaction_currencystringresponse_actionstringresponse_datetimedatetimeresolvedbooleanresolution_notesstring
INC0001anomaly_detectionblankfalseUSUSR101jamesnguyenjamesnguyen@mail.com2023-08-14T10:22:00Zcredential_compromiseDESK-A82XK4desktop192.168.6.23San Franciscofalsefalseblankpassword_reset2023-08-14T10:37:00ZtruePassword reset completed and user notified. No further suspicious activity detected during review.
INC0002manual_review98235.51trueGermanyUSR102liam.patelliam.patel@webmail.co.uk2022-12-28T15:05:00Zabnormal_transactionTAB-9G7RT1tablet88.134.201.45BerlinfalsefalseEURaccount_locked2022-12-28T15:16:00ZfalseAccount locked pending investigation of abnormal transaction. Awaiting user confirmation and forensic analysis.
INC0003automated_alertblankfalseCanadaUSR103alex.smithalex.smith@safeemail.com2024-01-08T13:47:00Zcredential_compromiseMOB-0Q4LPNmobile10.211.32.81Torontofalsefalseblankaccount_locked2024-01-08T14:03:00ZtrueAccount locked and credentials reset. User has confirmed no unauthorized changes.
INC0004user_reportblankfalseBrazilUSR104sophialopezsophialopez@outlook.com2023-04-03T08:30:00Zcontact_info_changeMOB-7TZLQ9mobile172.21.9.99Sao Paulotruefalseblankuser_notified2023-04-03T08:45:00ZtrueUser notified of contact information change. No further action required at this time.
INC0005anomaly_detection1500000trueSingaporeUSR105a.chena.chen@services.sg2024-04-16T19:11:00Zabnormal_transactionDESK-A7JQK1desktop203.116.42.88SingaporefalsefalseSGDaccount_locked2024-04-16T19:23:00ZfalseHigh-value transaction detected. Account locked for forensic review and regulatory notification.
INC0006automated_alertblankfalsePolandUSR106emma_davisemma_davis@securemail.com2023-11-09T16:28:00Zdevice_changeMOB-3V6WJ8mobile212.45.99.101Warsawfalsetrueblankpassword_reset2023-11-09T16:44:00ZtruePassword reset performed due to device change. User advised to monitor account activity.
INC0007manual_review500trueSpainUSR107luismartinluismartin@europemail.es2022-10-19T09:16:00Zabnormal_transactionTAB-8Y6FJ2tablet185.154.231.18MadridfalsefalseEURuser_notified2022-10-19T09:30:00ZtrueLow-value abnormal transaction detected. User notified and transaction reversed.
INC0008anomaly_detectionblankfalseIndiaUSR108meera.raomeera.rao@mailer.in2023-07-21T12:03:00Zcredential_compromiseDESK-PQ3N89desktop49.207.181.66Mumbaifalsetrueblankpassword_reset2023-07-21T12:19:00ZtruePassword reset initiated after credential compromise. User advised to update security questions.

What the 400 rows show

from the 400-row sample

Manual_review (detection method) stands out: 96 of its 106 rows have abnormal_transaction_detected = true, against 5 of 294 for the rest.

  • 25%abnormal_transaction_detected = true
  • 100,000median transaction_amount
  • 4device types
  • 5incident types
  • 5response actions
  • 10transaction currencies
Abnormal transaction detected rate by detection_methodabnormal_transaction_detected = true
0%50%100%4%anomaly_…5 of 12991%manual_r…96 of 1060%automate…0 of 900%user_rep…0 of 75
transaction_amount101 rows, in bands of 10M
0459086200040009050M100Mtransaction_amount →

Median 100,000, from 0.01 to 100,000,000.

geo_location_country365 rows with a value · 35 left blank
  1. US40
  2. Germany37
  3. Singapore28
  4. India26
  5. Brazil24
  6. Spain24
  7. Mexico21
  8. Canada20
  9. Russia20
  10. France18
21 columns by typefrom the column list below
  • string 14
  • float 1
  • datetime 2
  • boolean 4

Columns

21 columns in four groups
blueprint · 21 columns
columntypedescriptionexample
Text 14 columns
incident_idstringUnique identifier for the account takeover incidentuniqueINC0001
user_idstringUnique identifier for the affected user accountUSR101
usernamestringUsername of the affected accountjamesnguyen
emailstringEmail address associated with the accountjamesnguyen@mail.com
detection_methodstringMethod used to detect the unauthorized access (e.g., anomaly detection, manual review, automated alert)4 valuesanomaly_detection
incident_typestringType of unauthorized activity detected5 valuescredential_compromise
device_idstringIdentifier for the device used during the incident (if applicable)optionalDESK-A82XK4
device_typestringType of device used (e.g., mobile, desktop, tablet)mobile · desktop · tablet · unknown · optionaldesktop
ip_addressstringIP address from which the unauthorized access was attemptedoptional192.168.6.23
geo_location_countrystringCountry of origin for the access attempt, based on IP geolocationoptionalUS
geo_location_citystringCity of origin for the access attempt, based on IP geolocationoptionalSan Francisco
transaction_currencystringCurrency code for the transaction (e.g., USD, EUR)10 currencies · optionalEUR
response_actionstringAction taken in response to the incident (e.g., account locked, password reset, user notified)5 valuespassword_reset
resolution_notesstringAdditional notes or comments regarding the resolution of the incidentoptionalPassword reset completed …
Numbers 1 column
transaction_amountfloatAmount involved in the abnormal transaction (if applicable)0 or more · optional98235.51
Dates and times 2 columns
incident_datetimedatetimeDate and time when the unauthorized access attempt was detected2023-08-14T10:22:00Z
response_datetimedatetimeDate and time when the response action was takenoptional2023-08-14T10:37:00Z
True or false 4 columns
contact_info_changedbooleanIndicates if contact information (email, phone) was changed during the incidentfalse
device_changedbooleanIndicates if a new device was used for access during the incidentfalse
abnormal_transaction_detectedbooleanIndicates if abnormal transactions were detected during the incidentfalse
resolvedbooleanIndicates if the incident has been resolvedtrue

Use it for

  • abnormal trans…25%101 of 400 rowsabnormal transaction …4%anom…91%manu…0%auto…0%user…

    A finance dashboard

    The abnormal_transaction_detected rate, transaction_amount by detection_method and a breakdown of geo_location_country. Excel, Power BI or Tableau.

  • Why do 101 of 400 rows have abnormal_transaction_detected = true?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable incidents with user_id, username and email to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 21 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset400 rows21 columns
Yours1,000 rows21 columnsip_address: UK only

blueprint · account-takeover-detection

Behind this dataset

Same schema. As many rows as you need.

These 400 rows came out of a blueprint — 21 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Account access logs analyzed
  • Login from new device or location flagged
  • Multiple failed login attempts detected
  • Credential stuffing patterns identified
  • Contact information change triggers alert
  • Large or unusual transactions after access change
  • Multi-factor authentication bypass attempts
  • Account locked if takeover suspected
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
account-takeover-detection

What should your data show?

Preview 20 rows free
No signup. No card.