Remove Starter Digital Fingerprinting (DFP)

ci/release/update-version.sh

@@ -91,7 +91,6 @@ sed_runner "s/v${CURRENT_FULL_VERSION}-runtime/v${NEXT_FULL_VERSION}-runtime/g"
    examples/digital_fingerprinting/production/docker-compose.yml \
    examples/digital_fingerprinting/production/Dockerfile
 sed_runner "s/v${CURRENT_FULL_VERSION}-runtime/v${NEXT_FULL_VERSION}-runtime/g" examples/digital_fingerprinting/production/Dockerfile
-sed_runner "s|blob/branch-${CURRENT_SHORT_TAG}|blob/branch-${NEXT_SHORT_TAG}|g" examples/digital_fingerprinting/starter/README.md
 
 # examples/developer_guide
 sed_runner 's/'"VERSION ${CURRENT_FULL_VERSION}.*"'/'"VERSION ${NEXT_FULL_VERSION}"'/g' \

docs/source/basics/overview.rst

@@ -27,7 +27,7 @@ The Morpheus CLI is built on the Click Python package which allows for nested co
 together. At a high level, the CLI is broken up into two main sections:
 
  * ``run``
-    * For running AE, FIL, NLP or OTHER pipelines.
+    * For running FIL, NLP or OTHER pipelines.
  * ``tools``
     * Tools/Utilities to help set up, configure and run pipelines and external resources.
 
@@ -58,16 +58,13 @@ run:
    --help                          Show this message and exit.
 
    Commands:
-   pipeline-ae     Run the inference pipeline with an AutoEncoder model
    pipeline-fil    Run the inference pipeline with a FIL model
    pipeline-nlp    Run the inference pipeline with a NLP model
    pipeline-other  Run a custom inference pipeline without a specific model type
 
 
 Currently, Morpheus pipeline can be operated in four different modes.
 
- * ``pipeline-ae``
-    * This pipeline mode is used to run training/inference on the AutoEncoder model.
  * ``pipeline-fil``
     * This pipeline mode is used to run inference on FIL (Forest Inference Library) models such as XGBoost, RandomForestClassifier, etc.
  * ``pipeline-nlp``

docs/source/cloud_deployment_guide.md

@@ -32,7 +32,6 @@ limitations under the License.
   - [Verify Model Deployment](#verify-model-deployment)
   - [Create Kafka Topics](#create-kafka-topics)
 - [Example Workflows](#example-workflows)
-  - [Run AutoEncoder Digital Fingerprinting Pipeline](#run-autoencoder-digital-fingerprinting-pipeline)
   - [Run NLP Phishing Detection Pipeline](#run-nlp-phishing-detection-pipeline)
   - [Run NLP Sensitive Information Detection Pipeline](#run-nlp-sensitive-information-detection-pipeline)
   - [Run FIL Anomalous Behavior Profiling Pipeline](#run-fil-anomalous-behavior-profiling-pipeline)
@@ -383,10 +382,9 @@ kubectl -n $NAMESPACE exec deploy/broker -c broker -- kafka-topics.sh \
 
 This section describes example workflows to run on Morpheus. Four sample pipelines are provided.
 
-1. AutoEncoder pipeline performing Digital Fingerprinting (DFP).
-2. NLP pipeline performing Phishing Detection (PD).
-3. NLP pipeline performing Sensitive Information Detection (SID).
-4. FIL pipeline performing Anomalous Behavior Profiling (ABP).
+1. NLP pipeline performing Phishing Detection (PD).
+2. NLP pipeline performing Sensitive Information Detection (SID).
+3. FIL pipeline performing Anomalous Behavior Profiling (ABP).
 
 Multiple command options are given for each pipeline, with varying data input/output methods, ranging from local files to Kafka Topics.
 
@@ -424,44 +422,6 @@ helm install --set ngc.apiKey="$API_KEY" \
                morpheus-sdk-client
 ```
 
-
-### Run AutoEncoder Digital Fingerprinting Pipeline
-The following AutoEncoder pipeline example shows how to train and validate the AutoEncoder model and write the inference results to a specified location. Digital fingerprinting has also been referred to as **HAMMAH (Human as Machine <> Machine as Human)**.
-These use cases are currently implemented to detect user behavior changes that indicate a change from a human to a machine or a machine to a human, thus leaving a "digital fingerprint." The model is an ensemble of an autoencoder and fast Fourier transform reconstruction.
-
-Inference and training based on a user ID (`user123`). The model is trained once and inference is conducted on the supplied input entries in the example pipeline below. The `--train_data_glob` parameter must be removed for continuous training.
-
-```bash
-helm install --set ngc.apiKey="$API_KEY" \
-    --set sdk.args="morpheus --log_level=DEBUG run \
-      --edge_buffer_size=4 \
-      --pipeline_batch_size=1024 \
-      --model_max_batch_size=1024 \
-      pipeline-ae \
-        --columns_file=data/columns_ae_cloudtrail.txt \
-        --userid_filter=user123 \
-        --feature_scaler=standard \
-        --userid_column_name=userIdentitysessionContextsessionIssueruserName \
-        --timestamp_column_name=event_dt \
-        from-cloudtrail --input_glob=/common/models/datasets/validation-data/dfp-cloudtrail-*-input.csv \
-        --max_files=200 \
-        train-ae --train_data_glob=/common/models/datasets/training-data/dfp-cloudtrail-*.csv \
-        --source_stage_class=morpheus.stages.input.cloud_trail_source_stage.CloudTrailSourceStage \
-          --seed 42 \
-        preprocess \
-        inf-pytorch \
-        add-scores \
-        timeseries --resolution=1m --zscore_threshold=8.0 --hot_start \
-        monitor --description 'Inference Rate' --smoothing=0.001 --unit inf \
-        serialize \
-        to-file --filename=/common/data/<YOUR_OUTPUT_DIR>/cloudtrail-dfp-detections.csv --overwrite" \
-    --namespace $NAMESPACE \
-    <YOUR_RELEASE_NAME> \
-    morpheus-sdk-client
-```
-
-For more information on the Digital Fingerprint use cases, refer to the starter example and a more production-ready example that can be found in the `examples` source directory.
-
 ### Run NLP Phishing Detection Pipeline
 
 The following Phishing Detection pipeline examples use a pre-trained NLP model to analyze emails (body) and determine phishing or benign. Here is the sample data as shown below is used to pass as an input to the pipeline.

docs/source/developer_guide/contributing.md

@@ -375,7 +375,7 @@ Launching a full production Kafka cluster is outside the scope of this project;
 
 ### Pipeline Validation
 
-To verify that all pipelines are working correctly, validation scripts have been added at `${MORPHEUS_ROOT}/scripts/validation`. There are scripts for each of the main workflows: Anomalous Behavior Profiling (ABP), Humans-as-Machines-Machines-as-Humans (HAMMAH), Phishing Detection (Phishing), and Sensitive Information Detection (SID).
+To verify that all pipelines are working correctly, validation scripts have been added at `${MORPHEUS_ROOT}/scripts/validation`. There are scripts for each of the main workflows: Anomalous Behavior Profiling (ABP), Phishing Detection (Phishing), and Sensitive Information Detection (SID).
 
 To run all of the validation workflow scripts, use the following commands:
 

docs/source/developer_guide/guides/5_digital_fingerprinting.md

@@ -23,7 +23,7 @@ Every account, user, service, and machine has a digital fingerprint that represe
 To construct this digital fingerprint, we will be training unsupervised behavioral models at various granularities, including a generic model for all users in the organization along with fine-grained models for each user to monitor their behavior. These models are continuously updated and retrained over time​, and alerts are triggered when deviations from normality occur for any user​.
 
 ## Training Sources
-The data we will want to use for the training and inference will be any sensitive system that the user interacts with, such as VPN, authentication and cloud services. The digital fingerprinting example (`examples/digital_fingerprinting/README.md`) included in Morpheus ingests logs from [AWS CloudTrail](https://docs.aws.amazon.com/cloudtrail/index.html), [Azure Active Directory](https://docs.microsoft.com/en-us/azure/active-directory/reports-monitoring/concept-sign-ins), and [Duo Authentication](https://duo.com/docs/adminapi).
+The data we will want to use for the training and inference will be any sensitive system that the user interacts with, such as VPN, authentication and cloud services. The digital fingerprinting example (`examples/digital_fingerprinting/README.md`) included in Morpheus ingests logs from [Azure Active Directory](https://docs.microsoft.com/en-us/azure/active-directory/reports-monitoring/concept-sign-ins), and [Duo Authentication](https://duo.com/docs/adminapi).
 
 The location of these logs could be either local to the machine running Morpheus, a shared file system like NFS, or on a remote store such as [Amazon S3](https://aws.amazon.com/s3/).
 
@@ -44,54 +44,23 @@ Adding a new source for the DFP pipeline requires defining five critical pieces:
 1. A [`DataFrameInputSchema`](6_digital_fingerprinting_reference.md#dataframe-input-schema-dataframeinputschema) for the [`DFPFileToDataFrameStage`](6_digital_fingerprinting_reference.md#file-to-dataframe-stage-dfpfiletodataframestage) stage.
 1. A [`DataFrameInputSchema`](6_digital_fingerprinting_reference.md#dataframe-input-schema-dataframeinputschema) for the [`DFPPreprocessingStage`](6_digital_fingerprinting_reference.md#preprocessing-stage-dfppreprocessingstage).
 
-## DFP Examples
-The DFP workflow is provided as two separate examples: a simple, "starter" pipeline for new users and a complex, "production" pipeline for full scale deployments. While these two examples both perform the same general tasks, they do so in very different ways. The following is a breakdown of the differences between the two examples.
-
-### The "Starter" Example
-
-This example is designed to simplify the number of stages and components and provide a fully contained workflow in a single pipeline.
-
-Key Differences:
- * A single pipeline which performs both training and inference
- * Requires no external services
- * Can be run from the Morpheus CLI
-
-This example is described in more detail in `examples/digital_fingerprinting/starter/README.md`.
-
-### The "Production" Example
+## Production Deployment Example
 
 This example is designed to illustrate a full-scale, production-ready, DFP deployment in Morpheus. It contains all of the necessary components (such as a model store), to allow multiple Morpheus pipelines to communicate at a scale that can handle the workload of an entire company.
 
-Key Differences:
+Key Features:
  * Multiple pipelines are specialized to perform either training or inference
- * Requires setting up a model store to allow the training and inference pipelines to communicate
+ * Uses a model store to allow the training and inference pipelines to communicate
  * Organized into a docker-compose deployment for easy startup
  * Contains a Jupyter notebook service to ease development and debugging
  * Can be deployed to Kubernetes using provided Helm charts
  * Uses many customized stages to maximize performance.
 
 This example is described in `examples/digital_fingerprinting/production/README.md` as well as the rest of this document.
 
-### DFP Features
+## DFP Features
 
-#### AWS CloudTrail
-| Feature | Description |
-| ------- | ----------- |
-| `userIdentityaccessKeyId` | for example, `ACPOSBUM5JG5BOW7B2TR`, `ABTHWOIIC0L5POZJM2FF`, `AYI2CM8JC3NCFM4VMMB4` |
-| `userAgent` | for example, `Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 10.0; Trident/5.1)`, `Mozilla/5.0 (Linux; Android 4.3.1) AppleWebKit/536.1 (KHTML, like Gecko) Chrome/62.0.822.0 Safari/536.1`, `Mozilla/5.0 (Macintosh; U; PPC Mac OS X 10 7_0; rv:1.9.4.20) Gecko/2012-06-10 12:09:43 Firefox/3.8` |
-| `userIdentitysessionContextsessionIssueruserName` | for example, `role-g` |
-| `sourceIPAddress` | for example, `208.49.113.40`, `123.79.131.26`, `128.170.173.123` |
-| `userIdentityaccountId` | for example, `Account-123456789` |
-| `errorMessage` | for example, `The input fails to satisfy the constraints specified by an AWS service.`, `The specified subnet cannot be found in the VPN with which the Client VPN endpoint is associated.`, `Your account is currently blocked. Contact aws-verification@amazon.com if you have questions.` |
-| `userIdentitytype` | for example, `FederatedUser` |
-| `eventName` | for example, `GetSendQuota`, `ListTagsForResource`, `DescribeManagedPrefixLists` |
-| `userIdentityprincipalId` | for example, `39c71b3a-ad54-4c28-916b-3da010b92564`, `0baf594e-28c1-46cf-b261-f60b4c4790d1`, `7f8a985f-df3b-4c5c-92c0-e8bffd68abbf` |
-| `errorCode` | for example, success, `MissingAction`, `ValidationError` |
-| `eventSource` | for example, `lopez-byrd.info`, `robinson.com`, `lin.com` |
-| `userIdentityarn` | for example, `arn:aws:4a40df8e-c56a-4e6c-acff-f24eebbc4512`, `arn:aws:573fd2d9-4345-487a-9673-87de888e4e10`, `arn:aws:c8c23266-13bb-4d89-bce9-a6eef8989214` |
-| `apiVersion` | for example, `1984-11-26`, `1990-05-27`, `2001-06-09` |
-
-#### Azure Active Directory
+### Azure Active Directory
 | Feature | Description |
 | ------- | ----------- |
 | `appDisplayName` | for example, `Windows sign in`, `MS Teams`, `Office 365`​ |
@@ -104,14 +73,14 @@ This example is described in `examples/digital_fingerprinting/production/README.
 | `location.countryOrRegion` | country or region name​ |
 | `location.city` | city name |
 
-##### Derived Features
+#### Derived Features
 | Feature | Description |
 | ------- | ----------- |
 | `logcount` | tracks the number of logs generated by a user within that day (increments with every log)​ |
 | `locincrement` | increments every time we observe a new city (`location.city`) in a user's logs within that day​ |
 | `appincrement` | increments every time we observe a new app (`appDisplayName`) in a user's logs within that day​ |
 
-#### Duo Authentication
+### Duo Authentication
 | Feature | Description |
 | ------- | ----------- |
 | `auth_device.name` | phone number​ |
@@ -121,7 +90,7 @@ This example is described in `examples/digital_fingerprinting/production/README.
 | `reason` | reason for the results, for example, `User Cancelled`, `User Approved`, `User Mistake`, `No Response`​ |
 | `access_device.location.city` | city name |
 
-##### Derived Features
+#### Derived Features
 | Feature | Description |
 | ------- | ----------- |
 | `logcount` | tracks the number of logs generated by a user within that day (increments with every log)​ |
@@ -133,16 +102,16 @@ DFP in Morpheus is accomplished via two independent pipelines: training and infe
 
 ![High Level Architecture](img/dfp_high_level_arch.png)
 
-#### Training Pipeline
+### Training Pipeline
 * Trains user models and uploads to the model store​
 * Capable of training individual user models or a fallback generic model for all users​
 
-#### Inference Pipeline
+### Inference Pipeline
 * Downloads user models from the model store​
 * Generates anomaly scores per log​
 * Sends detected anomalies to monitoring services
 
-#### Monitoring
+### Monitoring
 * Detected anomalies are published to an S3 bucket, directory or a Kafka topic.
 * Output can be integrated with a monitoring tool.
 

docs/source/extra_info/known_issues.md

@@ -17,7 +17,6 @@ limitations under the License.
 
 # Known Issues
 
-- TrainAEStage fails with a Segmentation fault ([#1641](https://github.com/nv-morpheus/Morpheus/issues/1641))
 - `vdb_upload` example pipeline triggers an internal error in Triton ([#1649](https://github.com/nv-morpheus/Morpheus/issues/1649))
 
 Refer to [open issues in the Morpheus project](https://github.com/nv-morpheus/Morpheus/issues)

docs/source/getting_started.md

@@ -375,36 +375,6 @@ Commands:
   trigger         Buffer data until the previous stage has completed.
   validate        Validate pipeline output for testing.
 ```
-
-And for the AE pipeline:
-
-```
-$ morpheus run pipeline-ae --help
-Usage: morpheus run pipeline-ae [OPTIONS] COMMAND1 [ARGS]... [COMMAND2 [ARGS]...]...
-
-<Help Paragraph Omitted>
-
-Commands:
-  add-class        Add detected classifications to each message.
-  add-scores       Add probability scores to each message.
-  buffer           (Deprecated) Buffer results.
-  delay            (Deprecated) Delay results for a certain duration.
-  filter           Filter message by a classification threshold.
-  from-azure       Source stage is used to load Azure Active Directory messages.
-  from-cloudtrail  Load messages from a CloudTrail directory.
-  from-duo         Source stage is used to load Duo Authentication messages.
-  inf-pytorch      Perform inference with PyTorch.
-  inf-triton       Perform inference with Triton Inference Server.
-  monitor          Display throughput numbers at a specific point in the pipeline.
-  preprocess       Prepare Autoencoder input DataFrames for inference.
-  serialize        Includes & excludes columns from messages.
-  timeseries       Perform time series anomaly detection and add prediction.
-  to-file          Write all messages to a file.
-  to-kafka         Write all messages to a Kafka cluster.
-  train-ae         Train an Autoencoder model on incoming data.
-  trigger          Buffer data until the previous stage has completed.
-  validate         Validate pipeline output for testing.
-```
 Note: The available commands for different types of pipelines are not the same. This means that the same stage, when used in different pipelines, may have different options. Check the CLI help for the most up-to-date information during development.
 
 ## Next Steps