Evaluating Ensemble Robustness Against Adversarial Attacks

by   George Adam, et al.

Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of transferability poses grave security concerns as it leads to the possibility of attacking models in a black box setting, during which the internal parameters of the target model are unknown. In this paper, we seek to analyze and minimize the transferability of adversaries between models within an ensemble. To this end, we introduce a gradient based measure of how effectively an ensemble's constituent models collaborate to reduce the space of adversarial examples targeting the ensemble itself. Furthermore, we demonstrate that this measure can be utilized during training as to increase an ensemble's robustness to adversarial examples.


page 1

page 2

page 3

page 4


Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Deep learning models are vulnerable to adversarial examples. Transfer-ba...

Robustness to Adversarial Examples through an Ensemble of Specialists

We are proposing to use an ensemble of diverse specialists, where specia...

On the transferability of adversarial examples between convex and 01 loss models

We show that white box adversarial examples do not transfer effectively ...

On Evaluating Adversarial Robustness of Large Vision-Language Models

Large vision-language models (VLMs) such as GPT-4 have achieved unpreced...

Saliency Diversified Deep Ensemble for Robustness to Adversaries

Deep learning models have shown incredible performance on numerous image...

TREND: Transferability based Robust ENsemble Design

Deep Learning models hold state-of-the-art performance in many fields, b...

TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness

Adversarial Transferability is an intriguing property of adversarial exa...

Please sign up or login with your details

Forgot password? Click here to reset