differential privacy
A technique to ensure the privacy of individual data points in a dataset while sharing aggregated results, minimizing the risk of identifying specific individuals from the data.
- A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances
- A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input
- Adaptive Sigmoid Clipping for Balancing the Direction–Magnitude Mismatch Trade-off in Differentially Private Learning
- An Iterative Algorithm for Differentially Private $k$-PCA with Adaptive Noise
- Blameless Users in a Clean Room: Defining Copyright Protection for Generative Models
- Continual Release Moment Estimation with Differential Privacy
- Controlling The Spread of Epidemics on Networks with Differential Privacy
- Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy
- Deep Learning with Plausible Deniability
- Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programming
- Differential Privacy on Fully Dynamic Streams
- Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix
- Differentially Private High-dimensional Variable Selection via Integer Programming
- Differentially Private Relational Learning with Entity-level Privacy Guarantees
- Diffusion Federated Dataset
- Do You Really Need Public Data? Surrogate Public Data for Differential Privacy on Tabular Data
- Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping
- FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA
- GeoClip: Geometry-Aware Clipping for Differentially Private SGD
- Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning
- Instance-Optimality for Private KL Distribution Estimation
- InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
- Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy
- Multi-Class Support Vector Machine with Differential Privacy
- Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor
- On the Sample Complexity of Differentially Private Policy Optimization
- Optimal Best Arm Identification under Differential Privacy
- PREAMBLE: Private and Efficient Aggregation via Block Sparse Vectors
- Private Continual Counting of Unbounded Streams
- Private Hyperparameter Tuning with Ex-Post Guarantee
- Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
- Private Training Large-scale Models with Efficient DP-SGD
- Private Zeroth-Order Optimization with Public Data
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
- Purifying Approximate Differential Privacy with Randomized Post-processing
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
- Sequentially Auditing Differential Privacy
- Setting $\varepsilon$ is not the Issue in Differential Privacy
- Sketched Gaussian Mechanism for Private Federated Learning
- Struct-Bench: A Benchmark for Differentially Private Structured Text Generation
- Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries
- The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
- TokenSwap: A Lightweight Method to Disrupt Memorized Sequences in LLMs
- Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
- When Data Can't Meet: Estimating Correlation Across Privacy Barriers