The paper introduces ContinuousBench, a dynamic benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge and capabilities from sensitive…

The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

This paper proposes two post-processing techniques, random selection and linear combination, to construct a model that satisfies any desired differential privacy level without retraining, given a set…

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

The paper proposes using Differentially Private (DP) synthetic data, specifically through tabular synthesis and DP-Seeded Agent-Based Modeling (ABM), to resolve the conflict between data utility and p…

DP-SAPF introduces a saliency-aware parameter fine-tuning method that selectively identifies the most critical parameters for LoRA training, significantly improving the utility and fidelity of differe…

The paper proposes DPDL, a novel differential privacy algorithm for decentralized stochastic learning on non-IID data, which uses similarity-based calibration of perturbed cross-gradients to achieve p…

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

This paper investigates the vulnerability of Graph Neural Networks (GNNs) protected by Local Differential Privacy (LDP) to adversarial attacks, analyzing the interplay between privacy guarantees and a…

This paper empirically evaluates the effectiveness of Differential Privacy (DP) against Membership Inference Attacks (MIAs) in Federated Learning, demonstrating that a stacking attack strategy can det…

This paper develops a differential privacy framework to analyze and optimize privacy leakage from AI agent responses that utilize sensitive enterprise data, focusing on deriving optimal generation par…

The paper proposes a hashing-based framework using Differential Privacy to generate and release private datastores for retrieval-augmented AI systems, achieving strong privacy with minimal accuracy lo…

The paper introduces SMA-DP-SGD, a Spectral Memory-Aware Differential Privacy method that enhances standard DP-SGD by incorporating a memory branch derived from past noisy updates, improving model uti…

This paper corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.

This paper proposes a comprehensive federated learning workflow that enhances privacy and robustness by integrating personalized differential privacy budgets and client drift detection, achieving bett…

The paper proposes DP-MacAdam, a novel differentially private optimization algorithm that simultaneously uses adaptive gradient clipping and momentum, achieving improved model accuracy over existing m…