GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Navigating the Kore.ai XO Platform
Building a Virtual Assistant
Help & Learning Resources
Release Notes
Current Version
Recent Updates
Previous Versions
CONCEPTS
Design
Storyboard
Overview
FAQs
Conversation Designer
Overview
Dialog Tasks
Mock Scenes
Dialog Tasks
Overview
Navigate Dialog Tasks
Build Dialog Tasks
Node Types
Overview
Intent Node
Dialog Node
Dynamic Intent Node
GenAI Node
GenAI Prompt
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Process Node
Agent Transfer
Node Connections
Node Connections Setup
Sub-Intent Scoping
Entity Types
Entity Rules
User Prompts or Messages
Voice Call Properties
Knowledge AI
Introduction
Knowledge Graph
Introduction
Terminology
Build a Knowledge Graph
Manage FAQs
Knowledge Extraction
Import or Export Knowledge Graph
Prepare Data for Import
Importing Knowledge Graph
Exporting Knowledge Graph
Auto-Generate Knowledge Graph
Knowledge Graph Analysis
Answer from Documents
Alert Tasks
Small Talk
Digital Skills
Overview
Digital Forms
Digital Views
Introduction
Widgets
Panels
Session and Context Variables
Context Object
Intent Discovery
Train
NLP Optimization
ML Engine
Overview
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
Training Validations
NLP Configurations
NLP Guidelines
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
Intelligence
Introduction
Event Handlers
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Conversation Driven Dialog Builder
Sentinment Management
Tone Analysis
Default Standard Responses
Ignore Words & Field Memory
Test & Debug
Overview
Talk to Bot
Utterance Testing
Batch Testing
Conversation Testing
Conversation Testing Overview
Create a Test Suite
Test Editor
Test Case Assertion
Test Case Execution Summary
Glossary
Health and Monitoring
NLP Health
Flow Health
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
Deploy
Channels
Publishing
Versioning
Analyze
Introduction
Dashboard Filters
Overview Dashboard
Conversations Dashboard
Users Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Custom Meta Tags
Create Custom Dashboard
Create Custom Dashboard Filters
LLM and Generative AI Logs
NLP Insights
Task Execution Logs
Conversations History
Conversation Flows
Conversation Insights
Feedback Analytics
Usage Metrics
Containment Metrics
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Team Collaboration
Plan & Usage
Overview
Usage Plans
Templates
Support Plans
Invoices
Authorization
Conversation Sessions
Multilingual Virtual Assistants
Get Started
Supported Components & Features
Manage Languages
Manage Translation Services
Multiingual Virtual Assistant Behavior
Feedback Survey
Masking PII Details
Variables
Collections
IVR Settings
General Settings
Assistant Management
Manage Namespace
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
HOW TOs
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Composite Entities
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Intent Scoping using Group Node
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Bot Settings
  5. Redacting Personally Identifiable Information

Redacting Personally Identifiable Information

Personally identifiable information (PII) or sensitive personal information (SPI) refers to information that can be used alone or in conjunction with other information to identify, contact, or locate a single person or to identify an individual in context. Some examples of PII include Social Security Numbers, email addresses, credit card numbers, passport numbers, home addresses, and so forth.

Kore.ai allows you to redact any sensitive information that users share with your bots. When you enable redaction for an information type, you can transform its value into a pattern that doesn’t contain comprehensible data. The platform redacts any end-user input that matches the PII pattern in the context object, chat logs, chat history, and other places to protect sensitive data.

The original values are stored in a secure vault and can be used in a few scenarios to achieve business needs.  

    • If a PII value is used in Dialog Task transitions, the platform automatically uses the original value for the transition condition evaluation, such as validating the entity value’s format (for example,  checking if it is a valid number).
    • If a PII value is used in the Service Node definition, the platform uses the redacted value by default to make the service calls. You can choose to send the original data using the ‘De-identification of PII data’ configuration of the Service Node for scenarios like passing this value to the backend system for further processing. Refer to the Service Node post for more details
    • You may use the Redaction of PII Data configuration of the Entity Nodes to present the original values of a redacted entity value to the users for confirmation. Refer to the Entity Node post for more details.

The platform provides the following three modes to redact specified information types:

Option Description Example
Redaction Replaces the data with a unique random alphanumeric value An email address entered gets replaced with a random value such as jjh4ezb2
Replacement Replaces the data with a static value that you enter in the PII Redaction settings. If the static value entered is asdf1234, any email address entered is replaced with asdf1234
Mask with Character Replaces the first few and last few characters of the data with ‘+’ or ‘#’ symbols. You can select the number of characters to mask as well as the symbol for masking. If you configure the first four and last four characters to be masked with ‘+’, an email address such as helpdocs@kore.ai gets redacted as ++++docs@kor++++

How to Redact

      1. Open the bot for which you want to configure the PII settings.
      2. Select the Build tab from the top menu.
      3. From the left menu, click Configuration -> PII Settings.
      4. The PII Redaction page opens.
      5. If PII Redaction isn’t enabled for the bot, toggle the switch to Yes. The page now shows a list of information types whose redaction settings are configured by default.
      6. To activate the redaction of any of these out-of-the-box information types, toggle the switch next to them to Enable. To edit their redaction settings, click their name.
      7. To configure redaction settings for any other information types, click Add New on the top-right side of the PII Redaction page.

Configuration Fields

Field Description
Information Type Enter a name for the information type you want to secure, for example, Credit Card Number.
Definition Enter a regular expression for recognizing the information type from user entries. For example, a regex value for a Visa credit card could be similar to ^4[0-9]{12}(?:[0-9]{3})?$
Map Entities Map all the entities in the bot’s Dialog tasks that correspond to the information type.
Note: If you do not map entities corresponding to redacted information types, even valid user entries for those entities cause errors in the dialog tasks. For example, let’s say you have enabled redaction for email information type. When a user enters an email address for a bot entity, the platform immediately redacts the information even before the entity node captures it, as emails are set up for redaction. The entity node then receives redacted data, and since the entity is not mapped in the redaction settings, it assumes the redacted value as an invalid email entry. Whereas, if you map the entity in the redaction settings, the entity recognizes the data redacted and accepts it.
Display Type Select one of these modes to display the redacted data anywhere in the platform: Redaction, Replacement, Mask with Character.

Note: The value displayed would be prefixed with a platform generated random unique identifier. This is the key used internally to retrieve the original value in case of conditional transitions etc..

Configure Contextual Sensitive Data

The Kore.ai XO platform allows you to secure sensitive data input during the conversation. Enabling the redaction of sensitive data and utilizing custom regex patterns to identify and secure sensitive information is an effective approach.

You can enable the Sensitive Entity settings at the Entity Node to secure any sensitive user input. For example, PIN or OTP, usually, these are 4 to 6-digit numbers. Due to their sensitivity, these values must not be stored in plain text as part of the conversation logs and chat history because PINs or OTPs must be secured with the necessary privacy measures. Redacting or masking these values at the entity node level helps prevent them from being stored in plain text in conversation logs or chat history, reducing the risk of unauthorized access or misuse.

Use of custom regex patterns to define sensitive data allows the Virtual Assistant to identify and handle sensitive information appropriately based on the conversation context. This approach helps strike a balance between maintaining conversational functionality and safeguarding sensitive data.

Sensitive Data Use Case Scenarios

Scenario 1: The string patterns for sensitive data conflict or overlap in different contexts. For example, a password is 6~8 digits, and the phone number (TPN) is 9 to 12 digits long. In TPN cases, it’s very likely that the user misses typing a digit or two. However, due to the password PII pattern of 6~8 digits, the TPN gets masked as if it’s a password, and TPN entity recognition fails. In this scenario, you can enable the Sensitive Entity setting to redact and replace contextually sensitive data.

Scenario 2: A customer tries to change the password by interacting with the virtual assistant. Passwords being sensitive, you must secure them at all places. However, defining a PII pattern for passwords will potentially mask/redact any other input that matches the pattern.

The use of the Sensitive Entity (contextual) and the Personally Identifiable Information (PII) feature serve different purposes in handling sensitive data within the Kore.ai XO platform.

  • Personally Identifiable Information: Allows you to identify and redact or mask sensitive data that falls under common PII categories, such as social security numbers, email addresses, or credit card numbers. It provides a broad, predefined set of sensitive data patterns that can be automatically detected and handled uniformly across the entire conversation.
  • Sensitive Entity: Provides more fine-grained control and customization of redaction or replacement actions based on specific sensitive data contextual conditions. The Sensitive Entity option enables you to define rules or conditions that are specific to your use case, where the same sensitive data pattern might have different meanings or handling requirements depending on the context.

The need for sensitive nodes arises when you have overlapping or conflicting string patterns for sensitive data that require different treatment in different contexts. By configuring sensitive nodes, you can ensure that the platform correctly recognizes and handles sensitive data even when it matches multiple patterns.

For example, consider the scenario mentioned earlier, where a phone number (TPN) could be mistaken for a password due to overlapping string patterns. By using the sensitive entity option, you can define a context-specific rule that identifies TPNs and applies the appropriate redaction or replacement action, even if the same pattern matches a password in a different context.

The Sensitive Entity option provides flexibility in managing the handling of sensitive data within specific conversation flows, allowing you to tailor the behavior according to the requirements of your use case.

Both the PII and Sensitive Entity complement each other in providing comprehensive protection for sensitive data. While the PII feature offers broad coverage for common PII patterns, sensitive nodes enable you to handle sensitive data in a more granular and contextually aware manner, addressing specific challenges and custom use cases.

It’s recommended to leverage both features in combination to ensure comprehensive protection of sensitive data throughout your conversations. For more information, see the Entity Node article.

Redacting Personally Identifiable Information

Personally identifiable information (PII) or sensitive personal information (SPI) refers to information that can be used alone or in conjunction with other information to identify, contact, or locate a single person or to identify an individual in context. Some examples of PII include Social Security Numbers, email addresses, credit card numbers, passport numbers, home addresses, and so forth.

Kore.ai allows you to redact any sensitive information that users share with your bots. When you enable redaction for an information type, you can transform its value into a pattern that doesn’t contain comprehensible data. The platform redacts any end-user input that matches the PII pattern in the context object, chat logs, chat history, and other places to protect sensitive data.

The original values are stored in a secure vault and can be used in a few scenarios to achieve business needs.  

    • If a PII value is used in Dialog Task transitions, the platform automatically uses the original value for the transition condition evaluation, such as validating the entity value’s format (for example,  checking if it is a valid number).
    • If a PII value is used in the Service Node definition, the platform uses the redacted value by default to make the service calls. You can choose to send the original data using the ‘De-identification of PII data’ configuration of the Service Node for scenarios like passing this value to the backend system for further processing. Refer to the Service Node post for more details
    • You may use the Redaction of PII Data configuration of the Entity Nodes to present the original values of a redacted entity value to the users for confirmation. Refer to the Entity Node post for more details.

The platform provides the following three modes to redact specified information types:

Option Description Example
Redaction Replaces the data with a unique random alphanumeric value An email address entered gets replaced with a random value such as jjh4ezb2
Replacement Replaces the data with a static value that you enter in the PII Redaction settings. If the static value entered is asdf1234, any email address entered is replaced with asdf1234
Mask with Character Replaces the first few and last few characters of the data with ‘+’ or ‘#’ symbols. You can select the number of characters to mask as well as the symbol for masking. If you configure the first four and last four characters to be masked with ‘+’, an email address such as helpdocs@kore.ai gets redacted as ++++docs@kor++++

How to Redact

      1. Open the bot for which you want to configure the PII settings.
      2. Select the Build tab from the top menu.
      3. From the left menu, click Configuration -> PII Settings.
      4. The PII Redaction page opens.
      5. If PII Redaction isn’t enabled for the bot, toggle the switch to Yes. The page now shows a list of information types whose redaction settings are configured by default.
      6. To activate the redaction of any of these out-of-the-box information types, toggle the switch next to them to Enable. To edit their redaction settings, click their name.
      7. To configure redaction settings for any other information types, click Add New on the top-right side of the PII Redaction page.

Configuration Fields

Field Description
Information Type Enter a name for the information type you want to secure, for example, Credit Card Number.
Definition Enter a regular expression for recognizing the information type from user entries. For example, a regex value for a Visa credit card could be similar to ^4[0-9]{12}(?:[0-9]{3})?$
Map Entities Map all the entities in the bot’s Dialog tasks that correspond to the information type.
Note: If you do not map entities corresponding to redacted information types, even valid user entries for those entities cause errors in the dialog tasks. For example, let’s say you have enabled redaction for email information type. When a user enters an email address for a bot entity, the platform immediately redacts the information even before the entity node captures it, as emails are set up for redaction. The entity node then receives redacted data, and since the entity is not mapped in the redaction settings, it assumes the redacted value as an invalid email entry. Whereas, if you map the entity in the redaction settings, the entity recognizes the data redacted and accepts it.
Display Type Select one of these modes to display the redacted data anywhere in the platform: Redaction, Replacement, Mask with Character.

Note: The value displayed would be prefixed with a platform generated random unique identifier. This is the key used internally to retrieve the original value in case of conditional transitions etc..

Configure Contextual Sensitive Data

The Kore.ai XO platform allows you to secure sensitive data input during the conversation. Enabling the redaction of sensitive data and utilizing custom regex patterns to identify and secure sensitive information is an effective approach.

You can enable the Sensitive Entity settings at the Entity Node to secure any sensitive user input. For example, PIN or OTP, usually, these are 4 to 6-digit numbers. Due to their sensitivity, these values must not be stored in plain text as part of the conversation logs and chat history because PINs or OTPs must be secured with the necessary privacy measures. Redacting or masking these values at the entity node level helps prevent them from being stored in plain text in conversation logs or chat history, reducing the risk of unauthorized access or misuse.

Use of custom regex patterns to define sensitive data allows the Virtual Assistant to identify and handle sensitive information appropriately based on the conversation context. This approach helps strike a balance between maintaining conversational functionality and safeguarding sensitive data.

Sensitive Data Use Case Scenarios

Scenario 1: The string patterns for sensitive data conflict or overlap in different contexts. For example, a password is 6~8 digits, and the phone number (TPN) is 9 to 12 digits long. In TPN cases, it’s very likely that the user misses typing a digit or two. However, due to the password PII pattern of 6~8 digits, the TPN gets masked as if it’s a password, and TPN entity recognition fails. In this scenario, you can enable the Sensitive Entity setting to redact and replace contextually sensitive data.

Scenario 2: A customer tries to change the password by interacting with the virtual assistant. Passwords being sensitive, you must secure them at all places. However, defining a PII pattern for passwords will potentially mask/redact any other input that matches the pattern.

The use of the Sensitive Entity (contextual) and the Personally Identifiable Information (PII) feature serve different purposes in handling sensitive data within the Kore.ai XO platform.

  • Personally Identifiable Information: Allows you to identify and redact or mask sensitive data that falls under common PII categories, such as social security numbers, email addresses, or credit card numbers. It provides a broad, predefined set of sensitive data patterns that can be automatically detected and handled uniformly across the entire conversation.
  • Sensitive Entity: Provides more fine-grained control and customization of redaction or replacement actions based on specific sensitive data contextual conditions. The Sensitive Entity option enables you to define rules or conditions that are specific to your use case, where the same sensitive data pattern might have different meanings or handling requirements depending on the context.

The need for sensitive nodes arises when you have overlapping or conflicting string patterns for sensitive data that require different treatment in different contexts. By configuring sensitive nodes, you can ensure that the platform correctly recognizes and handles sensitive data even when it matches multiple patterns.

For example, consider the scenario mentioned earlier, where a phone number (TPN) could be mistaken for a password due to overlapping string patterns. By using the sensitive entity option, you can define a context-specific rule that identifies TPNs and applies the appropriate redaction or replacement action, even if the same pattern matches a password in a different context.

The Sensitive Entity option provides flexibility in managing the handling of sensitive data within specific conversation flows, allowing you to tailor the behavior according to the requirements of your use case.

Both the PII and Sensitive Entity complement each other in providing comprehensive protection for sensitive data. While the PII feature offers broad coverage for common PII patterns, sensitive nodes enable you to handle sensitive data in a more granular and contextually aware manner, addressing specific challenges and custom use cases.

It’s recommended to leverage both features in combination to ensure comprehensive protection of sensitive data throughout your conversations. For more information, see the Entity Node article.

Menu