Effective Universal Unrestricted Adversarial Attacks using a MOE Approach
arXiv:2103.00250 · doi:10.1007/978-3-030-72699-7_35
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.
References in corpus (9)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
- ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
- One pixel attack for fooling deep neural networks
- NIMA: Neural Image Assessment
- Unrestricted Adversarial Examples via Semantic Manipulation
- Adversarial Example Generation using Evolutionary Multi-objective Optimization
- Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
- They Might NOT Be Giants: Crafting Black-Box Adversarial Examples with Fewer Queries Using Particle Swarm Optimization