Imperial College London

Professor Emil Lupu

Faculty of EngineeringDepartment of Computing

Professor of Computer Systems
 
 
 
//

Contact

 

e.c.lupu Website

 
 
//

Location

 

564Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Co,
author = {Co, KT and Munoz, Gonzalez L and de, Maupeou S and Lupu, E},
publisher = {ACM},
title = {Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks},
url = {http://hdl.handle.net/10044/1/71700},
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - Deep Convolutional Networks (DCNs) have been shown to be vulnerable to adversarial examples—perturbed inputs specifically designed to produce intentional errors in the learning algorithms attest time. Existing input-agnostic adversarial perturbations exhibit interesting visual patterns that are currently unexplained. In this paper, we introduce a structured approach for generating Universal Adversarial Perturbations (UAPs) with procedural noise functions. Our approach unveils the systemic vulnerability of popular DCN models like Inception v3 and YOLO v3, with single noise patterns able to fool a model on up to 90% of the dataset. Procedural noise allows us to generate a distribution of UAPs with high universal evasion rates using only a few parameters. Additionally, we propose Bayesian optimization to efficiently learn procedural noise parameters to construct inexpensive untargeted black-box attacks. We demonstrate that it can achieve an average of less than 10 queries per successful attack, a 100-fold improvement on existing methods. We further motivate the use of input-agnostic defences to increase the stability of models to adversarial perturbations. The universality of our attacks suggests that DCN models may be sensitive to aggregations of low-level class-agnostic features. These findings give insight on the nature of some universal adversarial perturbations and how they could be generated in other applications.
AU - Co,KT
AU - Munoz,Gonzalez L
AU - de,Maupeou S
AU - Lupu,E
PB - ACM
TI - Procedural Noise Adversarial Examples for Black-Box Attacks on Deep Neural Networks
UR - http://hdl.handle.net/10044/1/71700
ER -