Image de couverture de livre

Clustering and Median Aggregation Improve Differentially Private Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Amin, Kareem, Avestimehr, Salman, Babakniya, Sara, Bie, Alex, Kong, Weiwei, Ponomareva, Natalia, Syed, Umar
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Private prediction for large-scale synthetic text generation
par: Amin, Kareem, et autres
Publié: (2024)

ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
par: Liu, Peihan, et autres
Publié: (2026)

Escaping Collapse: The Strength of Weak Data for Large Language Model Training
par: Amin, Kareem, et autres
Publié: (2025)

Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
par: Carranza, Aldo Gael, et autres
Publié: (2023)

Differentially Private Federated Learning without Noise Addition: When is it Possible?
par: Zhang, Jiang, et autres
Publié: (2024)

Differentially Private Distributed Inference
par: Papachristou, Marios, et autres
Publié: (2024)

Differentially Private Retrieval-Augmented Generation
par: Tang, Tingting, et autres
Publié: (2026)

Practical Considerations for Differential Privacy
par: Amin, Kareem, et autres
Publié: (2024)

Edge Private Graph Neural Networks with Singular Value Perturbation
par: Tang, Tingting, et autres
Publié: (2024)

Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling
par: Bayrooti, Jasmine, et autres
Publié: (2026)

Differentially Private De-identification of Dutch Clinical Notes: A Comparative Evaluation
par: Miranda, Michele, et autres
Publié: (2026)

Differentially Private Rankings via Outranking Methods and Performance Data Aggregation
par: Del Vasto-Terrientes, Luis
Publié: (2025)

Harnessing large-language models to generate private synthetic text
par: Kurakin, Alexey, et autres
Publié: (2023)

All Rivers Run to the Sea: Private Learning with Asymmetric Flows
par: Niu, Yue, et autres
Publié: (2023)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
par: Ngong, Ivoline C., et autres
Publié: (2024)

Differentially Private Optimization for Non-Decomposable Objective Functions
par: Kong, Weiwei, et autres
Publié: (2023)

How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
par: Ponomareva, Natalia, et autres
Publié: (2025)

Interpreting the Error of Differentially Private Median Queries through Randomization Intervals
par: Humphries, Thomas, et autres
Publié: (2026)

Improved Differentially Private Algorithms for Rank Aggregation
par: Hillebrand, Quentin, et autres
Publié: (2025)

ObfuscaTune: Obfuscated Offsite Fine-tuning and Inference of Proprietary LLMs on Private Datasets
par: Frikha, Ahmed, et autres
Publié: (2024)

Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers
par: Green, Tommaso, et autres
Publié: (2025)

Private Aggregate Queries to Untrusted Databases
par: Hafiz, Syed Mahbub, et autres
Publié: (2024)

SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference
par: Mishra, Abhijit, et autres
Publié: (2023)

Urania: Differentially Private Insights into AI Use
par: Liu, Daogao, et autres
Publié: (2025)

EPSVec: Efficient and Private Synthetic Data Generation via Dataset Vectors
par: Banayeeanzade, Amin, et autres
Publié: (2026)

Improved Algorithms for Differentially Private Language Model Alignment
par: Chen, Keyu, et autres
Publié: (2025)

Locally Differentially Private In-Context Learning
par: Zheng, Chunyan, et autres
Publié: (2024)

Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification
par: Han, Shanshan, et autres
Publié: (2023)

DP-BART for Privatized Text Rewriting under Local Differential Privacy
par: Igamberdiev, Timour, et autres
Publié: (2023)

Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt
par: Gu, Yujie, et autres
Publié: (2026)

A Survey on Private Transformer Inference
par: Li, Yang, et autres
Publié: (2024)

Fluent: Round-efficient Secure Aggregation for Private Federated Learning
par: Li, Xincheng, et autres
Publié: (2024)

Differentially Private Explanations for Clusters
par: Gilad, Amir, et autres
Publié: (2025)

Sub-optimal Learning in Meta-Classifier Attacks: A Study of Membership Inference on Differentially Private Location Aggregates
par: Liu, Yuhan, et autres
Publié: (2024)

Private Transformer Inference in MLaaS: A Survey
par: Li, Yang, et autres
Publié: (2025)

ContextLeak: Auditing Leakage in Private In-Context Learning Methods
par: Choi, Jacob, et autres
Publié: (2025)

Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models
par: Ruzzetti, Elena Sofia, et autres
Publié: (2025)

Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models
par: Huang, Chung-ju, et autres
Publié: (2026)

TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMs
par: Rajore, Tanmay, et autres
Publié: (2024)

Differentially Private Multi-objective Selection: Pareto and Aggregation Approaches
par: Farias, Victor A. E., et autres
Publié: (2024)