{"id":74892,"date":"2026-09-11T16:27:21","date_gmt":"2026-09-11T19:27:21","guid":{"rendered":"https:\/\/a3aengenharia.com\/?post_type=articles&p=74892"},"modified":"2026-09-11T17:09:43","modified_gmt":"2026-09-11T20:09:43","slug":"liveness-anti-spoofing-biometrics-pad-presentation-attacks-access-control","status":"publish","type":"articles","link":"https:\/\/a3aengenharia.com\/en-us\/content\/technical-articles\/liveness-anti-spoofing-biometrics-pad-presentation-attacks-access-control\/","title":{"rendered":"Liveness and Anti-Spoofing in Biometrics: PAD, Presentation Attacks, and Design Criteria"},"content":{"rendered":"\n

Liveness and anti-spoofing are mechanisms used to reduce the risk of a biometric system accepting an artificial, reproduced, or manipulated presentation as if it were a genuine characteristic of a person who is physically present. In standards terminology, the more precise concept is Presentation Attack Detection (PAD)<\/strong>: detecting attacks performed at the capture device during presentation and acquisition of the biometric characteristic.<\/p>\n\n\n\n

In access control, PAD does not replace FAR\/FMR, FRR\/FNMR, 1:1 verification, 1:N identification, multifactor authentication, authorization, or the physical barrier itself. It addresses a different threat. A matcher may distinguish genuine users from zero-effort impostors very effectively and still be vulnerable to a photograph, screen replay, mask, fingerprint replica, or another artifact presented to the sensor.<\/p>\n\n\n\n

For that reason, specifying only \u201cbiometrics with liveness\u201d is insufficient. A technically verifiable design needs to define the threat model, biometric modality, capture conditions, performance criteria, test evidence, failure behavior, and how compliance will be demonstrated in FAT, SAT, and commissioning. The objective is not to promise invulnerability, but to control a measurable risk without unduly degrading the experience of legitimate users.<\/p>\n\n\n\n

Liveness, anti-spoofing, and PAD are not the same thing<\/h2>\n\n\n\n

\u201cLiveness\u201d is the most widespread commercial and operational term for indicating that a sample appears to come from a living person who is present. \u201cAnti-spoofing\u201d is a broader expression used for mechanisms intended to hinder or detect forgery. The ISO\/IEC 30107 family uses Presentation Attack Detection<\/strong> because the standards problem is not limited to \u201cproving life\u201d: the focus is detecting presentations made to the capture device with the intent of interfering with operation of the biometric subsystem.<\/p>\n\n\n\n

This distinction prevents an imprecise specification. An algorithm may look for eye movement, texture, depth, spectral response, tissue properties, or other cues, but the design should not procure a technological \u201ctrick.\u201d It should procure verifiable performance against the presentation classes relevant to the risk<\/strong>.<\/p>\n\n\n\n

Term<\/td>Typical use<\/td>Interpretation limitation<\/td><\/tr>
Liveness<\/td>Verify signals associated with live presence<\/td>May suggest a narrower scope than the actual risk<\/td><\/tr>
Anti-spoofing<\/td>Prevent or detect forgery<\/td>Broad term that does not by itself define a test and acceptance method<\/td><\/tr>
PAD<\/td>Detect presentation attacks at the capture point<\/td>Does not cover every threat to the biometric system<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n

ISO\/IEC 30107-1:2023 limits PAD to attacks that occur at the capture device during presentation and acquisition of the biometric characteristic. Data injection after the sensor, API compromise, template theft, database tampering, administrative credential compromise, or controller bypass belong to other attack surfaces. This means that even a product with robust PAD still depends on appropriate architecture, cybersecurity, and access policy.<\/p>\n\n\n\n

The complete guide to access control systems<\/a> places biometrics within the broader chain of identification, authentication, authorization, decision, and actuation. PAD is an additional layer in that chain, not a substitute for the others.<\/p>\n\n\n\n

A presentation attack occurs at the capture point<\/h3>\n\n\n\n

A presentation attack occurs when an attacker presents a characteristic or artifact to the sensor with the objective of producing an improper response. In facial recognition, the threat class may include two-dimensional or three-dimensional presentations. In fingerprint recognition, it may include materials capable of reproducing patterns relevant to the sensor. Other modalities have their own attack surfaces.<\/p>\n\n\n\n

The design requirement should not become a catalog of attack recipes. What matters is establishing, at an appropriate level of detail, which presentation families are plausible for the asset, how critical the access is, and what evidence will demonstrate compatible resistance<\/strong>.<\/p>\n\n\n\n

Posi\u00e7\u00e3o do PAD na cadeia de decis\u00e3o biom\u00e9trica de controle de acesso<\/title>