Handwritten signatures

Identifies documents containing references to handwritten signatures in Australian contexts. This remains a concept detector over manual/wet/ink/specimen signature wording — it does not inspect handwriting pixels or capture a signature image. Bare "signed by" attribution (common in electronic/typed signature text) is corroborating evidence only, not a primary indicator.

Type

regex

Engine

boost_regex

Confidence

medium

Confidence justification

category-aware structural regex with anchor and context constraints replaces phrase-only detection. Added context gating and exclusion rules improve precision and reduce incidental matches.

Detection quality

Topic false positive

Jurisdictions

global

Regulations

AML/CTF Act (Cth), IPA 2009 (Qld), NDB Scheme (Cth), Privacy Act 1988 (Cth), GDPR

Frameworks

ISO 27001

Data categories

government-id, pii

Scope

wide

Risk rating

3

Platform compatibility

Purview: Compatible, GCP DLP: Compatible, Macie: Compatible, Zscaler: Compatible, Palo Alto: Degraded, Netskope: Unsupported

Pattern

(?is)\b(?:handwritten\s+signature|wet\s+signature|specimen\s+signature|signature\s+sample|signature\s+card|authorised\s+signature|authorized\s+signature|signature\s+verification|manual\s+signature)\b

Corroborative evidence keywords

handwritten signatures, handwritten, signatures, personal, identity, demographics, gait recognition, behavioral biometrics, behavioural biometrics, typing pattern, keystroke dynamics, signature dynamics, Touch ID, data record, database record, record set, data extract, data export, database table, spreadsheet (+17 more)

Proximity: 300 characters

Should match

• handwritten signature — Primary topic phrase match
• wet signature — Alternative topic phrase match
• specimen signature — Additional topic phrase match
• Wet handwritten signature captured on the deed. — Manual execution wording is unambiguous

Should not match

• unrelated generic text without domain phrases — No relevant topic phrases present
• placeholder value 12345 — Random text should not match topic-specific regex
• name disability — Generic word pair from old broad template should not match
• PDF signed by Alice using DocuSign. — Electronic "signed by" attribution no longer satisfies the primary (removed from the ID)
• The manager approved the request. — Approval alone has no signature concept

Known false positives

• Common words and phrases related to handwritten signatures appearing in policy documents, training materials, HR templates, or compliance guidelines without actual personal data. Mitigation: Require corroborative evidence keywords within the proximity window to confirm sensitive data context rather than general discussion.
• In Australian English, similar terminology used in formal or administrative contexts (education, professional documentation) that does not constitute sensitive data collection. Mitigation: Layer with additional contextual signals such as structured identifiers, form fields, or database column headers to distinguish sensitive records from general references.
• High-frequency pattern matches in large document corpora due to broad regex anchors. Expected match rate is significantly higher than specific identifier patterns. Mitigation: Tune confidence thresholds for bulk scanning. Consider using this pattern primarily as a pre-filter with secondary validation.

References

• https://www.oaic.gov.au/privacy/your-privacy-rights/your-personal-information/what-is-personal-information
• https://www.oaic.gov.au/privacy/your-privacy-rights/your-personal-information/what-is-sensitive-information
• https://www.oaic.gov.au/privacy/australian-privacy-principles-guidelines