FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning

Faiq Khalid, Muhammad Abdullah Hanif, Semeen Rehman, Junaid Qadir, Muhammad Shafique

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Deep neural networks (DNN)-based machine learning (ML) algorithms have recently emerged as the leading ML paradigm particularly for the task of classification due to their superior capability of learning efficiently from large dataseis. The discovery of a number of well-known attacks such as dataset poisoning, adversarial examples, and network manipulation (through the addition of malicious nodes) has, however, put the spotlight squarely on the lack of security in DNN-based ML systems. In particular, malicious actors can use these well-known attacks to cause random/targeted misclassification, or cause a change in the prediction confidence, by only slightly but systematically manipulating the environmental parameters, inference data, or the data acquisition block. Most of the prior adversarial attacks have, however, not accounted for the pre-processing noise filters commonly integrated with the ML-inference module. Our contribution in this work is to show that this is a major omission since these noise filters can render ineffective the majority of the existing attacks, which rely essentially on introducing adversarial noise. Apart from this, we also extend the state of the art by proposing a novel pre-processing noise Filter-aware Adversarial ML attack called FAdeML. To demonstrate the effectiveness of the proposed methodology, we generate an adversarial attack image by exploiting the "VGGNet" DNN trained for the "German Traffic Sign Recognition Benchmarks (GTSRB)" dataset, which despite having no visual noise, can cause a classifier to misclassify even in the presence of preprocessing noise filters.

Original languageEnglish (US)
Title of host publicationProceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages902-907
Number of pages6
ISBN (Electronic)9783981926323
DOIs
StatePublished - May 14 2019
Event22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019 - Florence, Italy
Duration: Mar 25 2019Mar 29 2019

Publication series

NameProceedings of the 2019 Design, Automation and Test in Europe Conference and Exhibition, DATE 2019

Conference

Conference22nd Design, Automation and Test in Europe Conference and Exhibition, DATE 2019
CountryItaly
CityFlorence
Period3/25/193/29/19

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality
  • Control and Optimization

Fingerprint Dive into the research topics of 'FAdeML: Understanding the Impact of Pre-Processing Noise Filtering on Adversarial Machine Learning'. Together they form a unique fingerprint.

Cite this