Skip to content
This is NOT an official site of the Government of Canada. Click here for the official AI registry.

Helpful Places

Government of Canada – DTPR AI Register

AI-Assisted Prohibited Item Detection for Airport Baggage Screening

Safety & Security · Enforcement

What it collects

About a measurement
Anonymized data
  • Multi-view and CT x-ray scan data of baggage contents. Materials absorb x-rays at different rates based on their density and atomic number, creating a contrast image used by the algorithm. The inputs are physical measurements of baggage contents, not personal data about travellers.
Operational data
Anonymized data
  • Defined data sets used for algorithm assessment and trial, including reference libraries of known explosives and threat masses prescribed by regulators (TSA and ECAC). These are standardized, non-personal operational datasets.
Run by
Canadian Air Transport Security Authority (CATSA)
Where
No fixed location
Kept
Not stated by the Helpful Places.
Shared with
Accountable organization, Vendor

What it is for

Safety & SecurityEnforcement

This system uses AI algorithms to automatically detect prohibited items and potential explosive threats in airport baggage using multi-view and CT x-ray scanners. The algorithms analyze x-ray images based on material density and atomic number to identify items of concern. It is currently in a trial and assessment phase, and all algorithms must be certified by international regulators using real explosive testing before deployment. The system does not directly process personal information about travellers.

What it collects and what happens to it

Data taken in

About a measurement
Anonymized data
  • Multi-view and CT x-ray scan data of baggage contents. Materials absorb x-rays at different rates based on their density and atomic number, creating a contrast image used by the algorithm. The inputs are physical measurements of baggage contents, not personal data about travellers.
Operational data
Anonymized data
  • Defined data sets used for algorithm assessment and trial, including reference libraries of known explosives and threat masses prescribed by regulators (TSA and ECAC). These are standardized, non-personal operational datasets.

Processing

Computer Vision
  • Object recognition algorithms interpret x-ray contrast images to identify shapes, densities, and compositions of items in baggage. Multi-view and CT x-ray imaging provides three-dimensional and multi-angle representations for analysis.
Classification & Prediction
  • The explosive detection algorithm compares analyzed density, atomic number, and size of items in a bag against a known list of explosives and threat masses to classify items as potential threats or non-threats. Results are compared against regulatory threat libraries.

What it does

Sensing (Perceptive AI)
Human decides
  • The system perceives and interprets x-ray images from multi-view and CT scanners, converting raw radiographic signals into structured detections of potential threat items. Human security officers review flagged items and make final screening decisions.
Deciding (Analytical AI)
Human decides
  • The explosive detection algorithm analyzes material densities, atomic numbers, and sizes of items in baggage and classifies them against a known threat reference list. The output is a flag or score that security personnel use to decide on further action.

Outputs

A recommendation or prediction
Anonymized data
  • The system produces automated alerts or flags identifying items of concern in scanned baggage for review by human security officers. The output is an advisory signal — final decisions about how to respond are made by trained screening personnel.

Run by

Canadian Air Transport Security Authority (CATSA)
  • CATSA is the federal agency responsible for air transport security screening in Canada. It deploys and assesses APIDS algorithms on its fleet of x-ray screening equipment at Canadian airports, in coordination with Transport Canada.

CATSA AI Register Entry 2526-CATSA-ACSTA-007

Built by

OEMs and Third-Party Algorithm Developers
  • Original equipment manufacturers (OEMs) and third-party companies develop the object recognition and explosive detection algorithms used in this system. Algorithms are developed by equipment suppliers and updated every several years based on new regulation.

CATSA AI Register Entry 2526-CATSA-ACSTA-007

Kept for

Not stated by the Helpful Places.

Shared with

Available to the accountable organization
  • X-ray scan data and algorithm outputs are available to CATSA and its security screening personnel for the purposes of air transport security screening.
Available to vendor
  • OEMs and third-party algorithm developers have access to relevant data sets and system performance results as part of the assessment, trial, and algorithm certification process.

Stored

Not stated by the Helpful Places.

How to read the colours

Can it identify you?

Anonymized data
Data about people with the link to who is broken. Stripped of identifiers, blurred, aggregated, or noised so this system can’t reasonably tie a record back to an individual.
Pseudonymous data
Each person’s data is tied to a token (hash, ID, template) that lets this system recognise the same person across events, but the token itself doesn’t reveal a name. Reidentification is possible with extra information.
Identifiable data
The data either contains a direct identifier (name, address, account name, recognisable face or voice, plate number) or carries a token this system uses to look up legal identity during processing.

Who completes the loop?

Human decides
This mode suggests; a person decides what to do next. The AI is always advisory — a human is in the loop on every decision. Example: a triage tool ranks cases for a clinician who chooses which to see first.
Human executes
This mode decides; a person carries out the result. Example: an optimizer plans the day’s trash-collection routes, and drivers run them.
Autonomous
This mode decides and acts on its own. No person reviews each decision or carries out the resulting action.

Definitions from the DTPR standard. Amber is about your data, violet about who decides. The fuller the shape and the deeper the colour, the more identifying the data or the less a person is involved.

What you can do

Ask about this system

Questions go to the Helpful Places, not the vendor.

Your rights

  • Right to Be Informed of AI UseTravellers passing through pre-board screening at Canadian airports are subject to automated prohibited item detection algorithms operating on x-ray equipment. This system is disclosed in CATSA's public AI register. The primary users are described as neither employees nor public — the system operates on baggage contents, not on personal data about travellers directly.

Risks and safeguards

  • Civil liberties harmFalse positives may subject travellers to secondary screening, delays, or unwarranted scrutiny, with potential for disproportionate impact.Safeguard: Algorithms are rigorously tested by TSA and ECAC regulators before certification using real explosives. CATSA works with Transport Canada to assess algorithm rollout. Human security officers make final screening decisions, and algorithms are updated periodically to reflect new regulation.