1/38
Comprehensive vocabulary flashcards covering privacy engineering objectives, differential privacy parameters, secure multi-party computation, federated learning attacks and defenses, k-anonymity, and pipeline security controls.
Workload Identity Least Privilege
The access control practice of provisioning a dedicated, scoped identity per data pipeline job (such as ingest, validate, and publish) rather than sharing a single privileged account capable of dropping tables.
Ephemeral Build Runner
A temporary compute environment that is provisioned on demand and automatically wiped after job completion, preventing sensitive residual artifacts (such as temporary files containing SSNs) from remaining accessible on shared build infrastructure.
Pipeline Quarantine
A data validation pattern in which records with invalid or impossible values (such as ages of 240 or negative GPAs) are automatically isolated into a separate store without crashing the entire processing pipeline.
Data Lineage Records
Metadata linking each published pipeline output to its specific input dataset version, transform code version, and job run ID, allowing teams to audit, reproduce outputs, and trace the downstream impact of bad inputs.
Additive Secret Sharing Modulo 100
A multi-party computation technique where a numerical secret s is divided into shares si that satisfy \big(\begin{matrix} \bigsum_{i} s_i \big) \bmod 100 = s\text{,} ensuring an isolated individual share reveals zero information about the true input value.
Malicious Adversary Model
An adversary model in secure multi-party computation where compromised participants actively deviate from the prescribed protocol, such as by transmitting falsified values to manipulate the reconstructed output.
Additively Homomorphic Encryption
A cryptosystem that allows a third-party compute service to perform additions directly over encrypted ciphertexts without decrypting or revealing the underlying plaintext inputs.
Model Poisoning
An adversarial machine learning attack where malicious participants inject corrupted weights or updates into a federated training pool, degrading model accuracy for targeted subgroups or planting backdoors.
Robust Aggregation
A federated learning defense mechanism that analyzes, clips, or excludes anomalous client updates to neutralize model poisoning attacks before model parameter averaging.
Membership Inference Attack
A privacy attack in which an adversary queries a trained machine learning model with a target individual's record to determine whether that record was included in the training set, exploiting abnormally high prediction confidence or low loss.
Differentially Private Training
A training framework (such as DP-SGD) that bounds and injects calibrated noise into weight gradients, preventing the trained model from memorizing individual records and mitigating membership inference attacks.
Gradient Inversion Attack
An attack against federated learning systems where an untrusted server reconstructs raw client training records and features directly from observed individual model gradient updates.
Secure Aggregation
A cryptographic federated learning protocol ensuring the central server can only observe the aggregate sum of all client updates, blinding the server to any single client's individual gradient update.
k-Anonymity
A property of a sanitized dataset requiring that every unique combination of quasi-identifiers appears at least k times, grouping records into equivalence classes of size at least k.
Distinct l-Diversity
An extension of k-anonymity requiring every quasi-identifier equivalence class to contain at least l well-represented, distinct sensitive attribute values.
Homogeneity Attack
A vulnerability in k-anonymous data where all records in an equivalence class share the identical sensitive attribute value, allowing an attacker to deduce a target's sensitive attribute with certainty despite k>1.
Generalization
A de-identification technique that transforms quasi-identifier values into broader ranges or categories (e.g., ages to intervals like 25–29 or ZIP codes to 90∗∗∗), increasing equivalence class sizes while decreasing data precision.
Predictability
A privacy engineering objective that enables reliable assumptions by individuals and operators about personal data processing and whether systems operate in an expected, disclosed manner.
Disassociability
A privacy engineering objective that enables the processing of personal data without allowing the linkage of data records to specific individuals outside the authorized context.
Manageability
A privacy engineering objective that provides granular operational controls to administer personal data, including enabling users to inspect, opt out of, or delete their stored historical information.
Privacy Risk Mitigation
A risk treatment approach that alters data collection practices or technical features (such as replacing granular borrowing titles with broad categories and requiring opt-in) to lessen privacy exposure.
Organizational Impact
The downstream operational, financial, legal, or reputational consequences borne by an entity—such as regulatory penalties, civil lawsuits, or loss of donor trust—following a privacy violation.
Differential Privacy Parameter δ
The failure probability parameter in approximate differential privacy; for a dataset of size N, δ must be chosen to be substantially smaller than N1 (e.g., δ=0.01 on N=10,000 is unacceptably large).
Query Repetition Attack
An attack where an adversary queries a differentially private interface repeatedly with the same question, allowing the average of returned answers to cancel out injected noise and continuously increase privacy loss.
Basic Composition Theorem
A differential privacy theorem stating that the overall privacy budget expended across multiple independent analyses on the same population equals the direct linear sum of the individual privacy parameters: ϵtotal=∑ϵi.
Longitudinal Pseudonym Linkage
A re-identification risk where assigning a persistent random token to an individual across multiple successive releases allows an adversary to track and link their records over time into an exhaustive personal profile.
Privacy Risk Statement
A structured risk articulation that explicitly binds a specific system data-handling action to its context and the resulting concrete harm experienced by affected individuals.
Targeted Re-Identification Attack
An adversary model where an attacker uses specific background knowledge about a single known individual (such as age, ZIP code, and hospital visit date) to search and locate that exact individual's record in a released dataset.
Function Creep
The gradual expansion of a software system or dataset's use beyond the originally specified operational purpose, such as when sensitive student risk scores are retained indefinitely in a multi-department query store.
Collusion in Multi-Party Computation
A vulnerability in multi-party computation where a subset of cooperating parties pool their private inputs and the final output (such as an average) to mathematically determine the private input of the remaining non-colluding party.
Unique Quasi-Identifier
A non-direct identifying data field or attribute value—such as the job title 'university president' appearing once in a staff survey—that uniquely isolates an individual within a dataset.
Short-Lived Workload Credentials
Temporary, auto-expiring authentication tokens issued to computational workloads, ensuring that stolen credentials become invalid quickly and cannot be exploited long-term.
Relative Error in Differential Privacy
The ratio of injected noise to the magnitude of the underlying true value; adding noise of identical scale causes a much larger relative distortion to small query counts (e.g., 20) than to large query counts (e.g., 20,000).
Laplace Mechanism Scale Parameter (b)
The dispersion parameter of the Laplace noise distribution, computed as b=ϵΔf, where Δf is the query's global sensitivity and ϵ is the allocated privacy budget.
Sample Uniqueness
A condition where a record's quasi-identifiers appear only once within an extracted sample of a population, which does not guarantee that the individual is unique within the broader underlying population.
Raw Zone Access Isolation
A data architecture boundary enforcing least privilege by restricting read access to unvalidated files containing PII exclusively to the dedicated ingestion and validation jobs moving records to curated zones.
Data-Dependent Clipping Bound
A differential privacy design flaw where a clipping threshold is chosen based on the maximum observed value within private data, causing the clipping parameter itself to leak sensitive information about outlier records.
Client-Level Differential Privacy
A differential privacy standard that bounds the aggregate influence of all data generated across a user's entire device or session history, rather than bounding the influence of each individual message or event.
Erroneous Record Linkage Harm
A privacy harm where an incorrect match generated from outdated or inaccurate auxiliary registries falsely attributes a sensitive condition or negative flag to an individual who does not have it.