ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks

17 July 2019

Papers citing "ART: Abstraction Refinement-Guided Training for Provably Correct Neural Networks"

6 / 6 papers shown

Title
Provably-Safe Neural Network Training Using Hybrid Zonotope Reachability Analysis Long Kiu Chung Shreyas Kousik 85 0 0 22 Jan 2025
DeepSaDe: Learning Neural Networks that Guarantee Domain Constraint Satisfaction Kshitij Goyal Sebastijan Dumancic Hendrik Blockeel 16 2 0 02 Mar 2023
Failing with Grace: Learning Neural Network Controllers that are Boundedly Unsafe Panagiotis Vlantis Leila J. Bridgeman Michael M. Zavlanos 15 0 0 22 Jun 2021
Scalable Synthesis of Verified Controllers in Deep Reinforcement Learning Zikang Xiong Suresh Jagannathan 11 6 0 20 Apr 2021
Robustness Verification for Transformers Zhouxing Shi Huan Zhang Kai-Wei Chang Minlie Huang Cho-Jui Hsieh AAML 4 103 0 16 Feb 2020
Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks Guy Katz Clark W. Barrett D. Dill Kyle D. Julian Mykel Kochenderfer AAML 222 1,818 0 03 Feb 2017