PingIntelligence

Training the ABS AI engine

For ABS to start predicting various attacks types, the model needs to be trained.

About this task

The number of hours (default: 24 hours) is configurable for model training.

Steps

  1. Set the value of training_period parameter using PingIntelligence Dashboard or the Global configuration update REST API.

    For more detailed information about training the AI model, see Managing AI engine training.

  2. Start the training.

    The training starts as soon as ABS receives the first API traffic from ASE and continues for the number of hours set in the attack_initial_training parameter. Training occurs automatically when a new API is added.

  3. Verify training completion.

    1. To check the ABS training status, use the ABS admin API, which returns the training duration and prediction mode. The API URL for the admin API is https://<ip>:<port>/v4/abs/admin.

      ip and port number are of the ABS machine.

      Result:

      The following is a snippet of the output of the admin API:

      "message": "training started at Thu Dec 26 12:32:59 IST 2019",
      "training_duration": "2 hours",
      "prediction": true

If the prediction variable is true, ABS has completed training and is discovering attacks. A false value means that ABS is still in training mode.

ABS only detects attacks after the training period is over. During training, no attacks are generated.