Differentiable Abstract Interpretation for Provably Robust Neural Networks
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.
Code (1)
Similar Papers 제목 키워드 기반
A Provable Defense for Deep Residual Networks
We present a training system, which can provably defend significantly larger neural networks than previously possible, including ResNet-34 and DenseNet-100. Our approach is based on differentiable abstract interpretation…
Adversarial DefenseNovel ConceptsExplaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
Despite significant advancements in post-hoc explainability techniques for neural networks, many current methods rely on heuristics and do not provide formally provable guarantees over the explanations provided. Recent w…
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation
We present a reinforcement learning (RL) framework in which the learned policy comes with a machine-checkable certificate of provable adversarial robustness. Our approach, called CAROL, learns a model of the environment.…
Adversarial RobustnessMuJoCoreinforcement-learningReinforcement Learning+1Abstract Interpretation on E-Graphs
Recent e-graph applications have typically considered concrete semantics of expressions, where the notion of equivalence stems from concrete interpretation of expressions. However, equivalences that hold over one interpr…
Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency
The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects. Recent methods learn to represent an object shape using a set of simple primitives to fit the …