Protected attribute

Also known as: sensitive attribute

On this page 7

A protected attribute is a personal characteristic, such as race, sex, age, religion or disability, that law or policy shields from discrimination, and that fairness analysis in AI ethics uses to define the groups whose outcomes must be compared. In machine learning it is also called a sensitive attribute, and it is usually written as A to distinguish it from the ordinary input features X and the outcome Y.

The concept links anti-discrimination law with statistical evaluation. A model may never receive a protected attribute as input and still treat groups differently, so practitioners treat the attribute as a reference variable for auditing rather than simply as a column to delete.

Where protected attributes come from

Protected attributes are defined by legal and ethical frameworks, not by data science. Which characteristics count depends on the jurisdiction and the domain, such as employment, credit, housing or public services, so the same model can face different protected lists in different markets.

The table below summarizes common sources and the characteristics they name. The lists are simplified; each instrument has its own scope, exceptions and case law.

SourceDomainExamples of protected characteristics
US Title VII of the Civil Rights ActEmploymentRace, color, religion, sex, national origin
US Age Discrimination in Employment ActEmploymentAge 40 and older
US Equal Credit Opportunity ActLendingRace, sex, marital status, age, receipt of public assistance
UK Equality Act 2010Employment, services, educationNine characteristics including disability and sexual orientation
EU Charter of Fundamental Rights, Article 21All EU lawSex, ethnic origin, religion, disability, age, sexual orientation and others
Selected legal sources of protected attributes

Data protection law adds a related but distinct category. The GDPR lists special categories of personal data, such as health and ethnic origin, whose processing is restricted. The overlap creates a known tension: auditing for bias may require collecting the very data that privacy rules limit.

How protected attributes enter fairness metrics

Fairness metrics use the protected attribute to split predictions into groups and compare them. Without knowing A for at least an evaluation sample, almost no group fairness metric can be computed, which is why the attribute is central even in systems that never use it for decisions.

Each metric conditions on the protected attribute in a different way, and the choice encodes a normative view of what equal treatment means.

CriterionCondition across groups of ATypical concern addressed
Demographic parityEqual positive prediction ratesUnequal access to opportunities
Equalized oddsEqual true and false positive ratesUnequal error burdens
Equal opportunityEqual true positive ratesQualified people being missed
Predictive parityEqual precision of positive predictionsScores meaning different things per group
Disparate impact ratioSelection rate ratio, often checked against 0.8Adverse impact under the four-fifths rule
Group fairness criteria defined over a protected attribute

These criteria are mutually incompatible in general: when base rates differ between groups, a classifier that is not perfect cannot satisfy calibration and equalized error rates at once. Choosing a metric is therefore a policy decision, not a purely technical one.

Why removing the attribute is not enough

Deleting the protected attribute from training data, an approach known as fairness through unawareness, rarely prevents discrimination. Other features often act as proxies that encode the same information, so the model can reconstruct group membership indirectly.

This effect is called proxy discrimination. Its strength depends on how much information the remaining features carry about A, which can be estimated by training a model to predict the protected attribute from the other inputs.

FeatureAttribute it may revealMechanism
Postal codeRace or ethnic originResidential segregation
First nameSex and ethnic originNaming conventions
Employment gapsSex or disabilityCaregiving or medical leave patterns
Graduation yearAgeDirect arithmetic relation
Purchase historyReligion or health statusDietary or medical product choices
Common proxies for protected attributes

Unawareness can even make bias harder to detect and correct, because mitigation methods such as reweighting or group-specific thresholds need the attribute to work.

Handling protected attributes in practice

Responsible handling separates decision-time use from audit-time use. In most regulated settings the attribute should not drive individual decisions directly, yet it should be available, under strict access controls, for measuring and mitigating disparities.

Regulation increasingly reflects this split. The EU AI Act permits providers of high-risk systems to process special categories of data where strictly necessary for bias detection and correction, subject to safeguards such as pseudonymization and deletion after use.

SituationRecommended approachReason
Attribute collected with consentStore separately for audits onlyEnables metrics without decision use
Attribute not collectedEstimate it with proxy inference for aggregate auditsAllows group-level checks with known error
Several attributes matterTest intersectional subgroupsHarms can hide in combinations such as age and sex
Small subgroupsReport confidence intervalsAvoids false conclusions from noise
Practical options for handling a protected attribute

Limitations and common misconceptions

Protected attributes are social categories with fuzzy and changing boundaries, while models treat them as fixed labels. Self-identification, mixed backgrounds and non-binary gender identities do not fit neatly into the categorical encodings that many datasets use.

  • Equal accuracy is not equal fairness: overall accuracy can be identical while error types differ sharply between groups.
  • Legal compliance is not the ceiling: an attribute absent from the law may still be ethically relevant in a given context.
  • Inferred attributes carry error: proxy estimates of race or sex can misclassify individuals and should be used only in aggregate.
  • One attribute at a time misses intersectional harm, which is a recurring finding in facial analysis audits.

The concept also connects to counterfactual fairness, which asks whether a decision would change if the protected attribute of the same person were different, a question that requires an explicit causal model rather than simple group statistics.

The idea in brief

A protected attribute is a personal trait such as age, sex or a disability. It should not count against someone in a decision. Laws name these traits because people were treated unfairly for them in the past.

Computers now help decide who gets a loan or a job interview. Checking fairness means comparing results for different groups. Hiding the trait from the computer is not enough. Clues like a home address or a first name can still reveal it.

A practical scenario

A mid-sized bank in the United States builds a credit scoring model for personal loans. The model never receives applicants’ race or sex, but the bank’s model risk team must still show that it does not produce unlawful disparate impact on protected groups.

Because race is not collected for most loan products, the team estimates it in aggregate with a surname and geography method and compares approval rates. The analysis shows a selection rate ratio of 0.74 for one group, below the common 0.8 benchmark. A feature review finds that a variable based on the applicant’s branch location acts as a strong proxy for ethnic origin.

The team replaces that variable with a direct measure of repayment capacity and retrains the model. The ratio rises to 0.86 with only a small loss in predictive performance, and the full analysis is documented for regulators and internal audit.