differential privacy

1010 papers

Explore in graph

Also known as

DPDL DP-SGD DP DPSGD MDP LDP

Co-occurring keywords

federated learning (1320) stochastic gradient descent (1088) sample complexity (1158) privacy preservation (376) privacy-preserving learning (115) regret bound (1918) privacy-preserving machine learning (99) large language model (12755) exponential mechanism (30) online learning (1770)

Papers

On the Exponential Convergence for Offline RLHF with Pairwise Comparisons AAAI 2026

Differentially Private Linear Programming: Reduced Sub-Optimality and Guaranteed Constraint Satisfaction AAAI 2026

Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering AAAI 2026

Towards Understanding Generalization in DP-GD: A Case Study in Training Two-Layer CNNs AAAI 2026

Estimating the True Distribution of Data Collected with Randomized Response AAAI 2026

Differentially Private Subspace Fine-Tuning for Large Language Models AAAI 2026

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing EACL 2026

PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure AAAI 2026

Privacy Preserving In-Context-Learning Framework for Large Language Models AAAI 2026

Venom: Liquid Diffusion-Guided Gradient Inversion for Breaking Differential Privacy in Federated Learning AAAI 2026

DP-NCB: Privacy Preserving Fair Bandits AAAI 2026

Private Frequency Estimation via Residue Number Systems AAAI 2026

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses AAAI 2026

PRISM: Privacy-Aware Routing for Adaptive Cloud–Edge LLM Inference via Semantic Sketch Collaboration AAAI 2026

Multi-Token Completion for Text Anonymization EACL 2026

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models EACL 2026

STAMP: Selective Task-Aware Mechanism for Text Privacy EACL 2026

DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data AAAI 2026

Efficient, Secure, Differentially Private Deep Learning in the Two-Server Model AAAI 2026

PrivSV: Differentially Private Steering Vector for Large Language Models AAAI 2026

Copyright Infringement Detection in Text-to-Image Diffusion Models via Differential Privacy AAAI 2026

RPGen: Robust and Differentially Private Synthetic Image Generation AAAI 2026

Improved Differentially Private Algorithms for Rank Aggregation AAAI 2026

PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation EMNLP 2025

Model-based Large Language Model Customization as Service EMNLP 2025