Improving Hierarchical Adversarial Robustness of Deep Neural Networks

02/17/2021
by   Avery Ma, et al.
0

Do all adversarial examples have the same consequences? An autonomous driving system misclassifying a pedestrian as a car may induce a far more dangerous – and even potentially lethal – behavior than, for instance, a car as a bus. In order to better tackle this important problematic, we introduce the concept of hierarchical adversarial robustness. Given a dataset whose classes can be grouped into coarse-level labels, we define hierarchical adversarial examples as the ones leading to a misclassification at the coarse level. To improve the resistance of neural networks to hierarchical attacks, we introduce a hierarchical adversarially robust (HAR) network design that decomposes a single classification task into one coarse and multiple fine classification tasks, before being specifically trained by adversarial defense techniques. As an alternative to an end-to-end learning approach, we show that HAR significantly improves the robustness of the network against ℓ_2 and ℓ_∞ bounded hierarchical attacks on the CIFAR-10 and CIFAR-100 dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/01/2019

Dropping Pixels for Adversarial Robustness

Deep neural networks are vulnerable against adversarial examples. In thi...
research
03/12/2019

Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models

Recent advances in machine learning, especially techniques such as deep ...
research
08/26/2021

A Hierarchical Assessment of Adversarial Severity

Adversarial Robustness is a growing field that evidences the brittleness...
research
10/25/2017

mixup: Beyond Empirical Risk Minimization

Large deep neural networks are powerful, but exhibit undesirable behavio...
research
07/13/2020

Nested Learning For Multi-Granular Tasks

Standard deep neural networks (DNNs) are commonly trained in an end-to-e...
research
02/24/2021

Multiplicative Reweighting for Robust Neural Network Optimization

Deep neural networks are widespread due to their powerful performance. Y...
research
11/03/2022

Exploring explicit coarse-grained structure in artificial neural networks

We propose to employ the hierarchical coarse-grained structure in the ar...

Please sign up or login with your details

Forgot password? Click here to reset