IoT Endpoint Anomaly Detection Logs

This dataset provides detailed, time-stamped logs of events and anomalies detected across remote IoT endpoints, including device identifiers, event types, severity scores, diagnostics, and compliance status. It is optimized for cybersecurity teams and AI/ML model training, supporting robust threat detection, incident response, and fleet management for edge computing environments.

  • last updated 19 Jan 2026
  • by GoMask
The brief that made it

Real-time monitoring and detection of security anomalies in IoT fleets

Sample rows

preview · 8 of 110 rows · all 14 columns
log_idstringevent_typestringseverity_scorefloatanomaly_flaggedbooleananomaly_typestringdevice_idstringdevice_typestringdevice_locationstringevent_timestampdatetimeevent_descriptionstringdiagnostic_summarystringresponse_actionstringcompliance_statusstringfleet_idstring
A9kL2m8QxZheartbeatblankfalseblankdev-1023AxsensorBuilding B, Floor 12024-05-09T08:24:17ZDevice sent routine heartbeat signal.Signal strength within normal range.blankcompliantfleet-east-01
C2pZ6wL4Nqanomaly0.74trueunauthorized_accesscam-2048BvcameraRemote Site 32024-05-09T09:01:45ZUnexpected movement detected outside scheduled hours.AI model flagged motion pattern as suspicious.alert_sentnon_compliantfleet-north-02
Q8rB5eJ1Tsdata_transmissionblankfalseblanksens-9987TrsensorWarehouse C, Gate 42024-05-09T10:15:29ZTemperature data transmitted to cloud.No data loss detected.blankcompliantfleet-west-03
F7sH4kW5Lmfirmware_updateblankfalseblankgtw-5111UxgatewayBuilding A, Floor 22024-05-09T11:03:13ZFirmware updated to v2.1.4.Update completed successfully.blankcompliantfleet-central-04
K5vM1xP8Rtloginblankfalseblankcam-2048BvcameraRemote Site 32024-05-09T12:44:22ZAdministrator login successful.User authenticated via 2FA.blankcompliantfleet-north-02
S3xT7rV2Ypanomaly0.62trueabnormal_trafficsens-9987TrsensorWarehouse C, Gate 42024-05-09T13:20:41ZTemperature spike detected.Model detected rapid sensor value change.alert_sentcompliantfleet-west-03
L2qD8vN6Zmheartbeatblankfalseblankgtw-5111UxgatewayBuilding A, Floor 22024-05-09T14:37:16ZDevice responded to status poll.No issues detected.blankcompliantfleet-central-04
E9gJ3fC7Qwconfiguration_changeblankfalseblankdev-1023AxsensorBuilding B, Floor 12024-05-09T15:50:08ZReporting interval changed from 5min to 10min.Change authorized by admin user.blankcompliantfleet-east-01

What the 110 rows show

from the 110-row sample

Anomaly (event type) stands out: 33 of its 33 rows have anomaly_flagged = true, against 1 of 77 for the rest.

  • 31%anomaly_flagged = true
  • 0.77median severity_score
  • 3response actions
  • 3compliance statuses
  • 4device types
  • 18device locations
Anomaly flagged rate by event_typeanomaly_flagged = true
0%50%100%8%login1 of 120%firmw…0 of 110%data_…0 of 18100%anoma…33 of …0%confi…0 of 90%heart…0 of 27
severity_score34 rows, in bands of 0.1
05101387960.40.71severity_score →

Median 0.77, from 0.41 to 0.97.

anomaly_type34 rows with a value · 76 left blank
  1. abnormal_traffic10
  2. device_failure8
  3. unauthorized_access7
  4. policy_violation4
  5. malware_detected4
  6. other1
14 columns by typefrom the column list below
  • string 11
  • float 1
  • datetime 1
  • boolean 1

Columns

14 columns in four groups
blueprint · 14 columns
columntypedescriptionexample
Text 11 columns
log_idstringUnique identifier for each anomaly detection log entryuniqueA9kL2m8QxZ
device_idstringUnique identifier for the IoT endpoint devicedev-1023Ax
device_typestringType or model of the IoT device (e.g., sensor, camera, gateway)4 typessensor
device_locationstringPhysical or logical location of the device (e.g., 'Building A, Floor 2', 'Remote Site 12')optionalBuilding B, Floor 1
event_typestringType of event detected (e.g., login, firmware_update, data_transmission, anomaly)7 valuesheartbeat
event_descriptionstringDetailed description of the eventoptionalImage data uploaded.
anomaly_typestringType of anomaly detected (e.g., unauthorized_access, abnormal_traffic, device_failure)6 values · optionalunauthorized_access
diagnostic_summarystringSummary of diagnostics or AI/ML model output for the eventoptionalNo data loss detected.
response_actionstringAction taken in response to the event or anomaly (e.g., alert_sent, device_isolated, no_action)5 values · optionalalert_sent
compliance_statusstringIndicates if the device/event is compliant with security policies (e.g., compliant, non_compliant, unknown)compliant · non_compliant · unknown · optionalcompliant
fleet_idstringIdentifier for the group or fleet to which the device belongsoptionalfleet-east-01
Numbers 1 column
severity_scorefloatNumerical score representing the severity of the anomaly (0.0-1.0)0 to 1 · optional0.74
Dates and times 1 column
event_timestampdatetimeDate and time when the event was logged2024-05-09T08:24:17Z
True or false 1 column
anomaly_flaggedbooleanIndicates if the event was flagged as an anomalyfalse

Use it for

  • anomaly flagged31%34 of 110 rowsanomaly flagged by ev…8%login0%firm…0%data…100%anom…

    A technology dashboard

    The anomaly_flagged rate, severity_score by event_type and a breakdown of anomaly_type. Excel, Power BI or Tableau.

  • Why do 34 of 110 rows have anomaly_flagged = 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 logs with device_id, device_type and device_location to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 14 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 dataset110 rows14 columns
Yours1,000 rows14 columnsdevice_location: UK only

blueprint · iot-endpoint-anomaly-detection-logs

Behind this dataset

Same schema. As many rows as you need.

These 110 rows came out of a blueprint — 14 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
  • Each log entry must include device ID, timestamp, event type, and anomaly flag
  • Severity scores are assigned on a scale of 1-10 based on ML-driven risk assessment
  • Anomalies are only flagged when deviation exceeds established operational baseline
  • Diagnostic summary must list probable source (firmware, network, sensor) for each anomaly
  • No device can have more than 3 critical anomalies per 24 hours
  • Only endpoints with edge connectivity status 'active' are monitored
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
iot-endpoint-anomaly-detection-logs

What should your data show?

Preview 20 rows free
No signup. No card.