Second-Order Adversarial Attack and Certifiable Robustness

By Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin. 2018

125 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Safety, Robustness & Interpretability

Citations in the corpus

Adversarial Training and Robustness for Multiple Perturbations (2019, methodology): “[23] B.”
Adversarial Training for Free! (2019, methodology): “3 we plot the cross-entropy loss projected along two directions in image space for the first few validation examples of CIFAR-10 [Li et al., 2018].”
Certified Adversarial Robustness via Randomized Smoothing (2019, methodology): “Tables for ImageNet and CIFAR-10 are in Appendix D. Prior randomized smoothing bounds Figure 6a plots the certified accuracy obtained using our bound alongside the certified accuracy obtained using the bounds of Lecuyer et al. (2019) and Li et al. (2018).”
Theoretical evidence for adversarial robustness through randomization: the case of the Exponential family (2019, neutral): “Initial results from [24] have been refined in [25], and [9].”
Unlabeled Data Improves Adversarial Robustness (2019, methodology): “Improving on previous work [24, 26], Cohen et al.”
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019, methodology): “[22] gave a stronger robustness guarantee using tools from information theory.”
Lipschitz-Certifiable Training with a Tight Outer Bound (2020, background): “This can make any classiﬁer to acquire a certiﬁed adversarial robustness by constructing a smoothed classiﬁer [22, 21, 6, 31].”
Towards Deep Learning Models Resistant to Adversarial Attacks (2017, background): “Indeed, subsequent work [20, 25] has found that PGD is in fact overestimating the `2-robustness of this model.”
Bayes-Probe: Distribution-Guided Sampling for Prediction Level Sets (2020, background): “…reveal that neural network predictions are locally unstable; i.e. an input can be slightly perturbed to make the network produce confident, incorrect predictions (Szegedy et al., 2013; Li et al., 2018a; Athalye et al., 2018; Carlini & Wagner, 2017; Nguyen et al., 2015; Goodfellow et al., 2014).”
Towards Stable and Efficient Training of Verifiably Robust Neural Networks (2019, methodology): “Besides these deterministic verification approaches, randomized smoothing can be used to certify the robustness of any model in a probabilistic manner (Cohen et al., 2019; Salman et al., 2019a; Lecuyer et al., 2018; Li et al., 2018).”