Search Results for author: Aounon Kumar

Found 8 papers, 4 papers with code

Certifying Model Accuracy under Distribution Shifts

no code implementations28 Jan 2022 Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution.

Policy Smoothing for Provably Robust Reinforcement Learning

no code implementations ICLR 2022 Aounon Kumar, Alexander Levine, Soheil Feizi

Prior works in provable robustness in RL seek to certify the behaviour of the victim policy at every time-step against a non-adaptive adversary using methods developed for the static setting.

Adversarial Robustness Image Classification +1

Center Smoothing: Certified Robustness for Networks with Structured Outputs

1 code implementation NeurIPS 2021 Aounon Kumar, Tom Goldstein

We extend the scope of certifiable robustness to problems with more general and structured outputs like sets, images, language, etc.

Adversarial Robustness Dimensionality Reduction +6

Tight Second-Order Certificates for Randomized Smoothing

1 code implementation20 Oct 2020 Alexander Levine, Aounon Kumar, Thomas Goldstein, Soheil Feizi

In this work, we show that there also exists a universal curvature-like bound for Gaussian random smoothing: given the exact value and gradient of a smoothed function, we compute a lower bound on the distance of a point to its closest adversarial example, called the Second-order Smoothing (SoS) robustness certificate.

Certifying Confidence via Randomized Smoothing

no code implementations NeurIPS 2020 Aounon Kumar, Alexander Levine, Soheil Feizi, Tom Goldstein

It uses the probabilities of predicting the top two most-likely classes around an input point under a smoothing distribution to generate a certified radius for a classifier's prediction.

Detection as Regression: Certified Object Detection by Median Smoothing

1 code implementation7 Jul 2020 Ping-Yeh Chiang, Michael J. Curry, Ahmed Abdelkader, Aounon Kumar, John Dickerson, Tom Goldstein

While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive.

object-detection Object Detection

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

1 code implementation ICML 2020 Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi

Notably, for $p \geq 2$, this dependence on $d$ is no better than that of the $\ell_p$-radius that can be certified using isotropic Gaussian smoothing, essentially putting a matching lower bound on the robustness radius.

Cannot find the paper you are looking for? You can Submit a new open access paper.