paper-with-me

Image Classification with Differential Privacy

1개 벤치마크 · 논문 8편 · 이 태스크의 논문 보기 →

Benchmarks

ImageNet

결과 4개

Most implemented

TAN Without a Burn: Scaling Laws of DP-SGD

2022-10-07 · 구현 1개

Papers

In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification

2024-01-01 · CVPR 2024 1 · Jinseong Park, Yujin Choi, Jaewook Lee

To alleviate the utility degradation of deep learning image classification with differential privacy (DP) employing extra public data or pre-trained models has been widely explored. Recently the use of in-distributio…

Diversityimage-classificationImage ClassificationImage Classification with Differential Privacy

Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy

2023-06-10 · Soroosh Tayebi Arasteh, Mahshad Lotfinia, Teresa Nolte, Marwin Saehn 외

Developing robust and effective artificial intelligence (AI) models in medicine requires access to large amounts of patient data. The use of AI models solely trained on large multi-institutional datasets can help with th…

DiagnosticDomain GeneralizationFairnessImage Classification with Differential Privacy+3

Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging

2023-02-03 · Soroosh Tayebi Arasteh, Alexander Ziller, Christiane Kuhl, Marcus Makowski 외

Artificial intelligence (AI) models are increasingly used in the medical domain. However, as medical data is highly sensitive, special precautions to ensure its protection are required. The gold standard for privacy pres…

Computed Tomography (CT)DiagnosticFairnessImage Classification with Differential Privacy+3

Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models

2023-01-30 · Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis

Differentially Private Stochastic Gradient Descent (DP-SGD) limits the amount of private information deep learning models can memorize during training. This is achieved by clipping and adding noise to the model's gradien…

Image ClassificationImage Classification with Differential Privacy

TAN Without a Burn: Scaling Laws of DP-SGD

2022-10-07 · Tom Sander, Pierre Stock, Alexandre Sablayrolles

Differentially Private methods for training Deep Neural Networks (DNNs) have progressed recently, in particular with the use of massive batches and aggregated data augmentations for a large number of training steps. Thes…

Image Classification with Differential Privacy

SmoothNets: Optimizing CNN architecture design for differentially private deep learning

2022-05-09 · Nicolas W. Remerscheid, Alexander Ziller, Daniel Rueckert, Georgios Kaissis

The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients. This introduces a reduction in model utility comp…

Deep LearningImage ClassificationImage Classification with Differential Privacy

전체 8편 보기 →