Buchumschlag

On Mitigating the Utility-Loss in Differentially Private Learning: A new Perspective by a Geometrically Inspired Kernel Approach

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Kumar, Mohit, Moser, Bernhard A., Fischer, Lukas
Format:	Preprint
Veröffentlicht:	2023
Schlagworte:	Machine Learning Artificial Intelligence Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Clients Collaborate: Flexible Differentially Private Federated Learning with Guaranteed Improvement of Utility-Privacy Trade-off
von: Li, Yuecheng, et al.
Veröffentlicht: (2024)

Differentially Private Deep Model-Based Reinforcement Learning
von: Rio, Alexandre, et al.
Veröffentlicht: (2024)

Differentially Private In-Context Learning with Nearest Neighbor Search
von: Koskela, Antti, et al.
Veröffentlicht: (2025)

Differentially Private Model Merging
von: Yin, Qichuan, et al.
Veröffentlicht: (2026)

Differentially Private Block-wise Gradient Shuffle for Deep Learning
von: Zagardo, David
Veröffentlicht: (2024)

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing
von: Piran, Fardin Jalil, et al.
Veröffentlicht: (2024)

Data-adaptive Differentially Private Prompt Synthesis for In-Context Learning
von: Gao, Fengyu, et al.
Veröffentlicht: (2024)

Smooth Sensitivity for Learning Differentially-Private yet Accurate Rule Lists
von: Ly, Timothée, et al.
Veröffentlicht: (2024)

DP-TabICL: In-Context Learning with Differentially Private Tabular Data
von: Carey, Alycia N., et al.
Veröffentlicht: (2024)

Provable Privacy with Non-Private Pre-Processing
von: Hu, Yaxi, et al.
Veröffentlicht: (2024)

Differentially Private Worst-group Risk Minimization
von: Zhou, Xinyu, et al.
Veröffentlicht: (2024)

RQP-SGD: Differential Private Machine Learning through Noisy SGD and Randomized Quantization
von: Feng, Ce, et al.
Veröffentlicht: (2024)

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning
von: Gluch, Greg, et al.
Veröffentlicht: (2025)

Improved Algorithms for Differentially Private Language Model Alignment
von: Chen, Keyu, et al.
Veröffentlicht: (2025)

Differentially Private Iterative Screening Rules for Linear Regression
von: Khanna, Amol, et al.
Veröffentlicht: (2025)

Provable Differentially Private Computation of the Cross-Attention Mechanism
von: Ke, Yekun, et al.
Veröffentlicht: (2024)

Evaluating Differentially Private Generation of Domain-Specific Text
von: Sun, Yidan, et al.
Veröffentlicht: (2025)

Differential Privacy Mechanisms in Neural Tangent Kernel Regression
von: Gu, Jiuxiang, et al.
Veröffentlicht: (2024)

Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
von: Islam, MD Shafikul, et al.
Veröffentlicht: (2026)

Differentially Private Synthetic Data Release for Topics API Outputs
von: Dick, Travis, et al.
Veröffentlicht: (2025)

Differentially Private Synthetic Data Generation Using Context-Aware GANs
von: Kotal, Anantaa, et al.
Veröffentlicht: (2025)

Differentially Private Preference Data Synthesis for Large Language Model Alignment
von: Gao, Fengyu, et al.
Veröffentlicht: (2026)

Reconstruction of Differentially Private Text Sanitization via Large Language Models
von: Pang, Shuchao, et al.
Veröffentlicht: (2024)

Differentially Private Publication of Electricity Time Series Data in Smart Grids
von: Shaham, Sina, et al.
Veröffentlicht: (2024)

Differentially Private Reinforcement Learning with Self-Play
von: Qiao, Dan, et al.
Veröffentlicht: (2024)

A Robust Framework for Secure Cardiovascular Risk Prediction: An Architectural Case Study of Differentially Private Federated Learning
von: Tertulino, Rodrigo, et al.
Veröffentlicht: (2026)

Rethinking Pruning for Backdoor Mitigation: An Optimization Perspective
von: Li, Nan, et al.
Veröffentlicht: (2024)

Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?
von: Du, Hao, et al.
Veröffentlicht: (2025)

GraMFedDHAR: Graph Based Multimodal Differentially Private Federated HAR
von: Halder, Labani, et al.
Veröffentlicht: (2025)

Too Good to be True? Turn Any Model Differentially Private With DP-Weights
von: Zagardo, David
Veröffentlicht: (2024)

dpmm: Differentially Private Marginal Models, a Library for Synthetic Tabular Data Generation
von: Mahiou, Sofiane, et al.
Veröffentlicht: (2025)

Class-Aware Adaptive Differential Privacy in Deep Learning for Sensor-Based Fall Detection
von: Sana, Joydeb Kumar
Veröffentlicht: (2026)

An Improved Privacy and Utility Analysis of Differentially Private SGD with Bounded Domain and Smooth Losses
von: Liang, Hao, et al.
Veröffentlicht: (2025)

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation
von: Wei, Chengkun, et al.
Veröffentlicht: (2025)

Differentially Private Distributed Inference
von: Papachristou, Marios, et al.
Veröffentlicht: (2024)

DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
von: Wu, Huiwen, et al.
Veröffentlicht: (2024)

SoK: A Systems Perspective on Compound AI Threats and Countermeasures
von: Banerjee, Sarbartha, et al.
Veröffentlicht: (2024)

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
von: Choquette-Choo, Christopher A., et al.
Veröffentlicht: (2023)

Differentially Private Learning Needs Better Model Initialization and Self-Distillation
von: Ngong, Ivoline C., et al.
Veröffentlicht: (2024)

Privacy Assessment of Federated Learning using Private Personalized Layers
von: Jourdan, Théo, et al.
Veröffentlicht: (2021)