MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
arXiv:2010.11463
Abstract
To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data representations, as a way to control the trade-off between data utility and vulnerability to inversion attacks. Our method is motivated by the theoretical insights of data separability in neural networking training and results on the hardness of model inversion. Empirically, by adjusting the separability of data representation, we show that there exist sweet-spots for data separability such that it is difficult to recover data during inference while maintaining data utility.
References in corpus (20)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Neural Tangent Kernel: Convergence and Generalization in Neural Networks
- A Convergence Theory for Deep Learning via Over-Parameterization
- Federated Optimization:Distributed Optimization Beyond the Datacenter
- Perceptual Adversarial Networks for Image-to-Image Transformation
- On Exact Computation with an Infinitely Wide Neural Net
- Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
- Split learning for health: Distributed deep learning without sharing raw patient data
- Recovery Guarantees for One-hidden-layer Neural Networks
- Supervised Contrastive Learning
- On the Convergence Rate of Training Recurrent Neural Networks
- Decentralized Collaborative Learning of Personalized Models over Networks
- Reliably Learning the ReLU in Polynomial Time
- Quadratic Suffices for Over-parametrization via Matrix Chernoff Bound
- Learning Non-overlapping Convolutional Neural Networks with Multiple Kernels
- The Computational Complexity of Training ReLU(s)
- Hardness of Learning Neural Networks with Natural Weights
- Learning Deep ReLU Networks Is Fixed-Parameter Tractable