MixTrain: Scalable Training of Formally Robust Neural Networks
By Shiqi Wang, Yizheng Chen, Ahmed Abdou, Suman Sekhar Jana. 2018
88 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Adversarial Training for Free! (2019, background): “Recently, there has been a surge of certified defenses [Wong and Kolter, 2017, Wong et al., 2018, Raghunathan et al., 2018a,b, Wang et al., 2018].”
- Certified Adversarial Robustness via Randomized Smoothing (2019, background): “Instead, a panoply of practical solutions have been proposed in the literature (Wong & Kolter, 2018; Wang et al., 2018a;b; Raghunathan et al., 2018a;b; Wong et al., 2018; Dvijotham et al., 2018b;a; Croce et al., 2018; Gehr et al., 2018; Mirman et al., 2018; Singh et al., 2018; Gowal et al., 2018;…”
- Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019, background): “On the bright side, these methods are more scalable and efficient which makes some of them useful for building certified defenses [38, 35, 36, 27, 28, 39, 10, 9, 7, 13, 26, 30, 15, 37, 40].”
- Towards Stable and Efficient Training of Verifiably Robust Neural Networks (2019, methodology): “Since the bound propagation process of a convex adversarial polytope is too expensive, several methods were proposed to improve its efficiency, like Cauchy projection (Wong et al., 2018) and dynamic mixed training (Wang et al., 2018a).”
- A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks (2019, methodology): “…gives a theoretical hardness proof based on a reduction from the set-cover problem; Neurify (Wang et al., 2018b) combines the relaxed bound with a branch-and-bound search to give concrete instances of adversarial example if they exist, and also uses the bound for training (Wang et al., 2018a).”
- Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond (2020, methodology): “Bounding the range of a neural network outputs given a certain amount of input perturbation has become an important theme for neural network verification and certified adversarial defense [48, 31, 45, 57].”
- Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Neural Network Robustness Verification (2021, methodology): “Additionally, another line of works train networks to enhance verified accuracy, typically using cheap incomplete verifiers at training time [42, 39, 25, 43, 18, 25, 47, 4, 32].”
- Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations (2020, methodology): “Several works have used it for certified adversarial defenses [80, 44, 75, 19, 88], but here we leverage it as a generic optimization tool for solving minimax functions involving neural networks.”