the latest in aiBeta

Private Training

Private training in machine learning aims to develop and deploy models without directly exposing sensitive training data. Current research heavily focuses on mitigating privacy risks in federated learning and other distributed training paradigms, exploring techniques like differential privacy, random data augmentation, and secure multi-party computation, often applied to vision transformers and other deep neural networks. This field is crucial for enabling the use of sensitive data in machine learning applications across healthcare, finance, and other sectors while addressing significant ethical and regulatory concerns around data privacy.

31papers

Papers

February 20, 2025

PPO-MI: Efficient Black-Box Model Inversion via Proximal Policy Optimization
Model Inversion Attack Optimization Purpose Black Box Model Inversion Attack Black Box Model Inversion Private Training Proximal Policy Optimization Policy Optimization

February 11, 2025

Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation
Private Training Mutual Distillation Federated Prompt Cooperation Privacy Leakage Label Inference Attack Federated Distillation Available Datasets

October 21, 2024

Subword Embedding from Bytes Gains Privacy without Sacrificing Accuracy and Complexity
Complexity Matter Sub Word Private Training Deep Neural Network

September 27, 2024

In-depth Analysis of Privacy Threats in Federated Learning for Medical Data
Depth Analysis Sensitive Patient Privacy Threat Privacy Risk Private Training Medical Image Medical Data

September 2, 2024

Defending against Model Inversion Attacks via Random Erasing
Model Inversion Attack Model Inversion High Dimensional Image Private Training

August 2, 2024

Privacy-Preserving Split Learning with Vision Transformers using Patch-Wise Random and Noisy CutMix
Cross Modal Manifold CutMix Vision Transformer Split Learning Private Training Random Participation Membership Inference Attack Differentially Private

June 18, 2024

Federated Learning with a Single Shared Image
Image SR Private Training Local Client Model Knowledge Distillation

June 3, 2024

Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Part Aware Transformer Data Leakage Tree Specie Differential Privacy Forest Environment Training Data Leakage Private Training Gradient Inversion Attack

May 6, 2024

The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
Policy Space New Attack Deep Learning Private Training Privacy Preservation Federated Learning Privacy Attack Financial Application

April 8, 2024

SoK: On Gradient Leakage in Federated Learning
Defense Method Gradient Inversion Attack Private Training Gradient Leakage

April 2, 2024

Federated Distillation: A Survey
Knowledge Distillation Federated Distillation Private Training Knowledge Transfer Timely Survey

March 26, 2024

Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning
Gradient Inversion Private Training Leakage Attack Pseudo Victim AttackER Data Reconstruction Attack

March 5, 2024

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models
Diverse Ensemble Byzantine Robust Federated Learning Contrastive Model Private Training State of the Art Defense

February 6, 2024

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
High Fidelity Timely Survey Model Inversion Attack Private Training Adversary Agent PRIvacy Leakage Model Inversion

December 21, 2023

Fine-grained Disentangled Representation Learning for Multimodal Emotion Recognition
Multimodal Emotion Recognition Private Training

October 16, 2023

Passive Inference Attacks on Split Learning via Adversarial Regularization
Private Training Split Learning Inference Attack Malicious Model Adversarial Regularization

October 12, 2023

Why Train More? Effective and Efficient Membership Inference via Memorization
Membership Inference Attack Membership Inference Private Training Adversary Agent Box Membership Inference Attack Limited Memorization

October 4, 2023

Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models
Fine Tuning Federated Prompt Private Training Black Box Pre Trained Model Large Pre Trained Model

February 24, 2023

Active Membership Inference Attack under Local Differential Privacy in Federated Learning
Private Training Membership Inference Attack Local Differential Privacy Membership Inference Differential Privacy Noise

December 16, 2022

Planting and Mitigating Memorized Content in Predictive-Text Language Models
Privacy Guarantee Language Model Private Training Plant Monitoring Differential Privacy Sensitive Data Verbatim Memorization