2000 character limit reached
Bridging the Gap: Differentially Private Equivariant Deep Learning for Medical Image Analysis
Published 9 Sep 2022 in eess.IV, cs.CR, cs.CV, and cs.LG | (2209.04338v2)
Abstract: Machine learning with formal privacy-preserving techniques like Differential Privacy (DP) allows one to derive valuable insights from sensitive medical imaging data while promising to protect patient privacy, but it usually comes at a sharp privacy-utility trade-off. In this work, we propose to use steerable equivariant convolutional networks for medical image analysis with DP. Their improved feature quality and parameter efficiency yield remarkable accuracy gains, narrowing the privacy-utility gap.
- Deep Learning with Differential Privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016.
- Group Equivariant Convolutional Networks. In International Conference of Machine Learning, 2016.
- Steerable CNNs. In International Conference on Learning Representations, 2017.
- The Algorithmic Foundations of Differential Privacy. Found. Trends Theor. Comput. Sci., 9:211–407, 2014.
- Augment Your Batch: Improving Generalization Through Instance Repetition. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8126–8135, 2020.
- Differentially private training of residual networks with scale normalisation. In ICML Theory and Practice of Differential Privacy Workshop, 2022.
- Differentially Private Learning Needs Better Features (or Much More Data). In International Conference on Learning Representations, 2020.
- General E(2)-Equivariant Steerable CNNs. Advances in Neural Information Processing Systems, 32, 2019.
- MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification. ArXiv, abs/2110.14795, 2021.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.