Alleviating Privacy Attacks via Causal Learning
Jul 12, 2020
Speakers
Shruti Tople
Speaker · 0 followers
Amit Sharma
Speaker · 0 followers
Aditya Nori
Speaker · 0 followers
About
Machine learning models, especially deep neural networks have been shown to reveal membership information of inputs in the training data. Such membership inference attacks are a serious privacy concern, for example, patients providing medical records to build a model that detects HIV would not want their identity to be leaked. Further, we show that the attack accuracy amplifies when the model is used to predict samples that come from a different distribution than the training set, which is often the case in real world applications. Therefore, we propose the use of causal learning approaches where a model learns the causal relationship between the input features and the outcome. An ideal causal model is known to be invariant to the training distribution and hence generalizes well to shifts between samples from the same distribution and across different distributions. First, we prove that models learned using causal structure provide stronger differential privacy guarantees than associational models under reasonable assumptions. Next, we show that causal models trained on sufficiently large samples are robust to membership inference attacks across different distributions of datasets and those trained on smaller sample sizes always have lower attack accuracy than corresponding associational models. Finally, we confirm our theoretical claims with experimental evaluation on 4 datasets with moderately complex Bayesian networks and an image dataset of colored MNIST. We observe that neural network-based associational models exhibit upto 80 Our results confirm the value of the generalizability of causal models in reducing susceptibility to privacy attacks.Machine learning models, especially deep neural networks have been shown to reveal membership information of inputs in the training data. Such membership inference attacks are a serious privacy concern, for example, patients providing medical records to build a model that detects HIV would not want their identity to be leaked. Further, we show that the attack accuracy amplifies when the model is used to predict samples that come from a different distribution than the training set, which is often…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Unsupervised Risk Estimation with Domain-Invariant Predictors
Watch later
Few-shot Domain Adaptation by Causal Mechanism Transfer
Watch later
Latent Bernoulli Autoencoder
Watch later
Jiri Fajtl, …
Uncertainty quantification using martingales for misspecified Gaussian Processes
Watch later
