Image Classification with Differential Privacy
1개 벤치마크 · 논문 8편 · 이 태스크의 논문 보기 →
Benchmarks
ImageNet
Most implemented
Unlocking High-Accuracy Differentially Private Image Classification through Scale
Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
Preserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy
Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models
TAN Without a Burn: Scaling Laws of DP-SGD
Papers
In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
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 PrivacyPreserving privacy in domain transfer of medical AI models comes at no performance costs: The integral role of differential privacy
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+3Private, fair and accurate: Training large-scale, privacy-preserving AI models in medical imaging
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+3Equivariant Differentially Private Deep Learning: Why DP-SGD Needs Sparser Models
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 PrivacyTAN Without a Burn: Scaling Laws of DP-SGD
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 PrivacySmoothNets: Optimizing CNN architecture design for differentially private deep learning
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