Effective Universal Unrestricted Adversarial Attacks using a MOE Approach

TL;DR

This paper introduces a multi-objective nested evolutionary algorithm that generates universal, effective, and undetectable adversarial image attacks in black-box scenarios by applying image filters.

Contribution

It presents a novel multi-objective nested evolutionary approach for creating universal adversarial examples using image filters, considering both attack success and detection rates.

Findings

Effective generation of undetectable adversarial attacks

High success rate in black-box scenarios

Filters can fool classifiers while evading detection

Abstract

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested evolutionary algorithm to generate universal unrestricted adversarial examples in a black-box scenario. The unrestricted attacks are performed through the application of well-known image filters that are available in several image processing libraries, modern cameras, and mobile applications. The multi-objective optimization takes into account not only the attack success rate but also the detection rate. Experimental results showed that this approach is able to create a sequence of filters capable of generating very effective and undetectable attacks.