Adversarial Training and Provable Robustness: A Tale of Two Objectives

08/13/2020
by   Jiameng Fan, et al.
0

We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks. We formulate the training problem as a joint optimization problem with both empirical and provable robustness objectives and develop a novel gradient-descent technique that can eliminate bias in stochastic multi-gradients. We perform both theoretical analysis on the convergence of the proposed technique and experimental comparison with state-of-the-arts. Results on MNIST and CIFAR-10 show that our method can match or outperform prior approaches for provable l infinity robustness.

READ FULL TEXT

Authors

page 16

05/17/2021

An SDE Framework for Adversarial Training, with Convergence and Robustness Analysis

Adversarial training has gained great popularity as one of the most effe...
06/07/2019

Inductive Bias of Gradient Descent based Adversarial Training on Separable Data

Adversarial training is a principled approach for training robust neural...
02/24/2022

Large-scale Stochastic Optimization of NDCG Surrogates for Deep Learning with Provable Convergence

NDCG, namely Normalized Discounted Cumulative Gain, is a widely used ran...
04/19/2021

Provable Robustness of Adversarial Training for Learning Halfspaces with Noise

We analyze the properties of adversarial training for learning adversari...
02/10/2021

Bayesian Inference with Certifiable Adversarial Robustness

We consider adversarial training of deep neural networks through the len...
03/01/2021

A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness

Alongside the well-publicized accomplishments of deep neural networks th...
05/24/2021

Skew Orthogonal Convolutions

Training convolutional neural networks with a Lipschitz constraint under...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.