Alleviating Privacy Attacks via Causal Learning
arXiv:1909.12732
Abstract
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such privacy risks are exacerbated when a model's predictions are used on an unseen data distribution. To alleviate privacy attacks, we demonstrate the benefit of predictive models that are based on the causal relationships between input features and the outcome. We first show that models learnt using causal structure generalize better to unseen data, especially on data from different distributions than the train distribution. Based on this generalization property, we establish a theoretical link between causality and privacy: compared to associational models, causal models provide stronger differential privacy guarantees and are more robust to membership inference attacks. Experiments on simulated Bayesian networks and the colored-MNIST dataset show that associational models exhibit upto 80% attack accuracy under different test distributions and sample sizes whereas causal models exhibit attack accuracy close to a random guess.
arXiv commentAccepted at International Conference on Machine Learning, 2020
References in corpus (12)
- Playing Atari with Deep Reinforcement Learning
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- Counterfactual Fairness
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
- Domain Adaptation: Learning Bounds and Algorithms
- Invariant Risk Minimization
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
- A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
- Learning Bayesian Networks with the bnlearn R Package
- Domain Generalization using Causal Matching
- Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences
- Auditing Data Provenance in Text-Generation Models