arXiv:2607. 07471v1 Announce Type: cross Abstract: Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness.
Machine learning models are increasingly deployed in high-stakes domains, raising concerns about both privacy and fairness. Differential Privacy (DP) has become a gold standard for privacy-preserving data analysis, while fairness-aware mechanisms aim to mitigate discrimination against underrepresented groups.
arXiv:2607. 16620v1 Announce Type: cross Abstract: Differential privacy (DP) is increasingly deployed to limit membership inference risk in machine-learning systems.
arXiv:2606. 08259v1 Announce Type: new Abstract: This paper investigates the problem of generating synthetic tabular data with differential privacy (DP) guarantees, enabling data sharing in sensitive domains.
arXiv:2502. 17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks.
The paper demonstrates that causal fairness mechanisms can be applied across a wide range of synthetic data generators, including marginal‑based, GAN, and diffusion models, each with differentially private variants. By porting three fairness definitions to nine generators and testing them on Adult and COMPAS datasets, the authors show that the causal diffusion backbone consistently produces the fairest data releases while maintaining high fidelity. The fairness cuts have minimal impact on data quality, costing downstream classifiers only about $0.07$ to $0.15$ AUC on average, and adding privacy guarantees does not reduce fairness.
The paper argues that evaluating anonymity in synthetic data generation must focus on the generative model rather than just the resulting dataset. It interprets GDPR definitions of personal data and anonymization under realistic model-access scenarios, mapping these to state‑of‑the‑art privacy attacks. The authors conclude that synthetic data alone is insufficient for anonymization, and that Differential Privacy offers stronger protection than Similarity‑based Privacy Metrics.
arXiv:2512. 03238v2 Announce Type: replace-cross Abstract: High quality data is needed to unlock the full potential of AI for end users.
The paper investigates how to maintain causal fairness when releasing synthetic data by applying the DECAF framework across nine different synthetic data generators from three families (marginals-based, GAN, and diffusion) and three levels of differential privacy. Experiments on Adult and COMPAS datasets show that the causal diffusion backbone consistently produces the fairest data with fidelity comparable to the marginals tier, while the fairness cuts have minimal impact on downstream classifier performance and do not degrade privacy guarantees.
arXiv:2606. 20461v1 Announce Type: new Abstract: Machine learning models have been shown to exhibit discriminatory outcomes or degraded performance for individuals at the intersection of multiple sensitive attributes, such as race and gender.
arXiv:2607. 14607v1 Announce Type: cross Abstract: Machine learning (ML) models deployed in sensitive domains such as healthcare, law enforcement, and finance must satisfy not only utility requirements but also fairness and privacy guarantees.
We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is the same across sensitive groups. Our approach departs from existing work on fair SDG, that address the problem of correcting for undue biases in the observed distribution, hence redefining SDG as learning a distribution that is not that of the real data.
arXiv:2607. 28945v1 Announce Type: new Abstract: Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias.