← Back to papers
2018 ICML ICML 2018

Differentiable Abstract Interpretation for Provably Robust Neural Networks

Abstract

We introduce a scalable method for training robust neural networks based on abstract interpretation. We present several abstract transformers which balance efficiency with precision and show these can be used to train large neural networks that are certifiably robust to adversarial perturbations.

🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning
🧭 Keyword Pioneer — certifiable robustness
🐣 Hot Topic Early Bird — adversarial perturbation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Matthew Mirman , Timon Gehr , Martin Vechev

Topics

Artificial Intelligence > Core AI > AI Safety Deep Learning > Architectures > Neural Networks

Keywords

adversarial robustness adversarial perturbation abstract interpretation certifiable robustness neural network
Download PDF

Related papers

Rectify Heterogeneous Models with Semantic Mapping 2018
Bayesian Optimization of Combinatorial Structures 2018
The Well-Tempered Lasso 2018
Approximation Algorithms for Cascading Prediction Models 2018
Classification from Pairwise Similarity and Unlabeled Data 2018