Hub
Pricing About
WorkflowWorkflow

Anonymize Sensitive Data for Bank Assistant Chatbots

Release 5.3PresidioPIIPersonally Identifiable InformationAI
knime profile image
Versionv1.0 KNIME AP 5.3 ReleaseLatest, created on 
Jul 10, 2024 12:13 PM
Drag & drop
Like
Download workflow
Workflow preview

This workflow uses Presidio nodes within KNIME to anonymize sensitive information while working with third-party AI models in the KNIME Analytics Platform environment.

Using the Presidio nodes, you can easily identify Personally Identifiable Information (PII) and anonymize it before passing it to chat large language models, significantly reducing the risk of sensitive data leaks and ensuring a secure data environment.

You can download and run the workflow directly in your KNIME Analytics Platform. For optimal performance, we recommend using the latest version of the KNIME Analytics Platform.

Workflow Details

  1. Creating Fake Customer Message

    • A fake bank customer message is created, complaining about some unauthorized transactions on their credit card, along with the system message to use in the Chat Model Prompter node.

  2. Identifying PII with Presidio Analyzer

    • The Presidio Analyzer node identifies the following PII entities: Credit Card, Email, and Person. After running the node, we check how many entities the node has found.

  3. Anonymizing PII with Presidio Anonymizer

    • Using the information from the Presidio Analyzer node, the Presidio Anonymizer node anonymizes the entities with random ones (names and emails).

  4. Passing Anonymized Data to Chat Model

    • Once the data is anonymized, the customer issue is passed to OpenAI using the Chat Model Prompter node. The node is configured as follows:

      1. System Message: Instruct the AI to behave like a bank's virtual assistant.

      2. User Message: Contains the request from the customer.

      3. Past Conversations: Includes a welcome message.

  5. Deanonymizing AI Response

    • When the AI assistant produces the response, the generated content is passed to the Presidio Deanonymizer node to restore the original entities. In the node output you can compare the anonymized and deanonymized outputs.

  6. Visualizing Chat

    • Finally, the chat is plotted with the original data from the customer.

External resources

  • Microsoft Presidio
Loading deploymentsLoading ad hoc jobs

Used extensions & nodes

Created with KNIME Analytics Platform version 5.3.0
  • Go to item
    KNIME AI ExtensionTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 5.3.0

    knime profile image
    knime
  • Go to item
    KNIME Base nodesTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 5.3.0

    knime profile image
    knime
  • Go to item
    KNIME Presidio ExtensionTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 5.3.0

    knime profile image
    knime
  • Go to item
    KNIME Quick FormsTrusted extension

    KNIME AG, Zurich, Switzerland

    Version 5.3.0

    knime profile image
    knime

Legal

By using or downloading the workflow, you agree to our terms and conditions.

KNIME
Open for Innovation

KNIME AG
Talacker 50
8001 Zurich, Switzerland
  • Software
  • Getting started
  • Documentation
  • Courses + Certification
  • Solutions
  • KNIME Hub
  • KNIME Forum
  • Blog
  • Events
  • Partner
  • Developers
  • KNIME Home
  • Careers
  • Contact us
Download KNIME Analytics Platform Read more about KNIME Business Hub
© 2025 KNIME AG. All rights reserved.
  • Trademarks
  • Imprint
  • Privacy
  • Terms & Conditions
  • Data Processing Agreement
  • Credits