Detection Categories

Blur organizes detection into four risk categories: contact data and addresses, names and entities, financial identifiers, and sensitive traits. Every category exposes granular per-type toggles, so each detection type can be turned on or off independently to match your specific privacy requirements.

The free tier masks exactly three types: people's names, email addresses, and phone numbers. Every other detection type listed below is unlocked on the Individual and Enterprise plans.

Contact & Addresses

Email addresses and phone numbers are included in the free tier. Locations & addresses and links & URLs require Individual or Enterprise.

Contact data is detected so teams can ask for writing or analysis help without pasting raw personal contact data into a model request.

Detection types in this category:

• Email addresses (free) in any standard format, e.g. name@company.com
• Phone numbers (free) in domestic and international formats
• Locations & addresses (Individual & Enterprise): street addresses, city/state/zip combinations, and mailing addresses
• Links & URLs (Individual & Enterprise)

This is one of the most commonly triggered categories because contact information frequently appears in prompts that involve drafting emails, summarizing meeting notes, or processing customer data.

Names & Entities

People's names are included in the free tier. Companies, job titles, schools, and institutions require Individual or Enterprise.

Blur replaces names and organization references with clean placeholders that preserve the intent of the prompt without exposing the original context.

Detection types in this category:

• People's names (free): first names, last names, and full names
• Companies & job titles (Individual & Enterprise)
• Schools & institutions (Individual & Enterprise)

The detection engine uses a combination of pattern matching and entity recognition to distinguish names from common words, minimizing false positives while catching a broad range of name formats.

Financial & Regulated Identifiers

Individual & Enterprise

SSNs, credit card numbers, and other high-risk identifiers are surfaced aggressively because these are the highest consequence values to leak into third-party model traffic. A single exposed SSN or card number in an AI prompt creates immediate regulatory and liability risk.

Examples of what this category catches:

• Social Security Numbers (SSN) in standard and common alternative formats
• Credit and debit card numbers (Visa, Mastercard, Amex, Discover patterns)
• Bank account and routing numbers
• Tax identification numbers (EIN, ITIN)

This category uses strict pattern matching optimized for low false-negative rates. It is designed to err on the side of flagging potential matches rather than missing genuine sensitive data.

Sensitive Attributes

Individual & Enterprise

Health details, dates of birth, and other sensitive personal descriptors are treated as review-worthy fields so users can decide what leaves the browser. This category is particularly relevant for teams in healthcare, HR, insurance, and legal verticals where personal attributes frequently appear in work context.

Detection types in this category:

• Health & medical: medical conditions and health-related terms
• Age, gender & identity: age references and demographic descriptors
• Religion & beliefs
• Relationships & family
• Sensitive dates: dates of birth and other personal dates

Because these traits are context-dependent, the detection engine flags potential matches for user review rather than automatically masking them. This gives users the final say on whether a flagged item is genuinely sensitive in their specific use case.

Aggressive Mode

Individual & Enterprise

When enabled, Aggressive Mode applies stricter matching thresholds across all active categories. This results in more items being flagged for review, which is appropriate for teams with zero-tolerance policies around data exposure in AI prompts.

Aggressive Mode is recommended for:

• Teams handling regulated data (HIPAA, PCI, SOX)
• Security-conscious organizations during initial rollout
• Use cases where the cost of a missed detection is high

Smart Placeholders

Individual & Enterprise

By default, Blur replaces detected items with generic placeholder tokens (e.g., [NAME], [EMAIL]). Smart Placeholders upgrade this behavior by generating contextually appropriate replacement values that make the resulting prompt read more naturally.

For example:

• "John Smith" might be replaced with "Alex Rivera" instead of [NAME]
• "john.smith@acme.com" might be replaced with "alex.rivera@example.com" instead of [EMAIL]

This is useful when the AI model's response quality depends on having realistic-looking input data rather than obvious placeholder tokens.

Settings sync across sites

Detection toggles, granular per-type controls, mask style, and dark mode are stored in the extension's shared storage and apply automatically across every supported site (ChatGPT, Claude, and Gemini) within the same browser profile. Configure detection once and it follows you wherever you use AI.