Differential Privacy
Overview
Differential privacy studies algorithms whose outputs reveal limited information about any individual record, even when an attacker knows other data. Common approaches add calibrated noise to statistics or clipped gradients, use randomized response for local privacy, or combine privacy with subsampling, shuffling, and secure aggregation. These methods support private statistical estimation, machine learning, federated learning, and synthetic data generation, including for images, tables, and text; evaluation often measures both task utility and membership-inference risk. A central tension is that stronger guarantees can reduce accuracy or increase computational cost, while task-specific structure and tighter privacy accounting may improve the trade-off without resolving all deployment risks.
Latest papers
314 papers39 papers in the last four weeks, up 5% on the four weeks before. 0.3% of all new papers.
Differentially Private Mixing of Public Datasets Improves Private Learning
DP-ES: Differentially Private Evolution Strategies for Prompt Optimization
Asymptotically Optimal Best Arm Identification with Fixed-Budget under Differential Privacy
Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level Privacy
Differential Privacy of Gradient Descent on Perturbed Objectives
HXAI: Hierarchical Privacy-Preserving Explainable AI in Distributed Energy Systems
Certification-Based Differentially Private Learning
PrivCert: Certifying Statement Support under Differential Privacy
Where Privacy Belongs: Placement Diagnosis and Certified Selection for Private Counterfactual Explanations on Graphs
A Sharp Transition in Data Reconstruction under Differential Privacy
Understanding Private Evolution as Learning-Augmented Clustering
Vanilla Policy Optimization Is Both Optimal and Differentially Private for Stochastic Contextual Bandits
Geometry-Adaptive Mechanisms for Private Synthetic Data
Gap-free Differentially Private PCA for Gaussian Data
Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores
Private Decentralized Optimization with Noise Reduction and Bias Correction
An Exposition of GPT Astra's Proof of Lower Bound on DP Continual Counting
Gap-Free Streaming PCA Beyond Rank-One Updates: Near-Optimal Rates and Applications to Differential Privacy
Empirical Auditing of Edge-Private Graph Generators
Improved Private Sparse Covariance Estimation with Multiscale Threshold Tests
Locally Private Inference for Riemannian Stochastic Optimization
Differentially Private Semantic Plans for Aggregate Insight Generation
URANIA provides end-to-end differential privacy (DP) for summaries of data-dependent clusters. However, its cluster--keyword release does not directly provide collection-wide aggregates for semantic concepts defined independently of the protected corpus. Records may express several concepts, records expressing the same concept may be assigned to different clusters, and cluster identities need not correspond across analyses. Consequently, cluster-level statistics do not directly provide comparable measurements of predefined concepts across collections or repeated analyses. We introduce DP-SPIN, a trusted-curator framework for aggregate measurement and summarization over semantic concepts fixed independently of the protected target records. Each record is mapped to a bounded sparse nonnegative vector over these concepts, whose sum forms a semantic sketch. A differentially private mechanism releases a semantic plan containing admitted concepts and noisy masses; normalized semantic-support values and support bins are obtained by post-processing. For user-level privacy, each user's aggregate contribution is clipped to a fixed bound. The language model receives only the plan and fixed decoding instructions, while a public verifier checks concept mentions, reported values, comparisons, and rank claims against the released plan. The final summary is differentially private by post-processing. We establish record- and user-level DP guarantees under add/drop and replacement adjacency. We evaluate DP-SPIN under record-level privacy on CFPB complaint narratives, Amazon All Beauty reviews, and Yelp restaurant reviews, and under user-level privacy on Amazon and Yelp. We compare DP-SPIN with non-private plan and summary references, DP keyword and category histogram baselines, and a URANIA-style baseline with a fixed public keyword vocabulary.