Security for machine learning-based systems: Attacks and challenges during training and inference

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

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

Abstract

The exponential increase in dependencies between the cyber and physical world leads to an enormous amount of data which must be efficiently processed and stored. Therefore, computing paradigms are evolving towards machine learning (ML)-based systems because of their ability to efficiently and accurately process the enormous amount of data. Although ML-based solutions address the efficient computing requirements of big data, they introduce security vulnerabilities into the systems, which cannot be addressed by traditional monitoring-based security measures. Therefore, this paper first presents a brief overview of various security threats in machine learning, their respective threat models and associated research challenges to develop robust security measures. To illustrate the security vulnerabilities of ML during training, inferencing and hardware implementation, we demonstrate some key security threats on ML using LeNet and VGGNet for MNIST and German Traffic Sign Recognition Benchmarks (GTSRB). Moreover, based on the security analysis of ML-Training, we also propose an attack that has very less impact on the inference accuracy. Towards the end, we highlight the associated research challenges in developing security measures and provide a brief overview of the techniques used to mitigate such security threats.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 International Conference on Frontiers of Information Technology, FIT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages327-332
Number of pages6
ISBN (Electronic)9781538693551
DOIs
StatePublished - Jan 16 2019
Event16th International Conference on Frontiers of Information Technology, FIT 2018 - Islamabad, Pakistan
Duration: Dec 17 2018Dec 19 2018

Publication series

NameProceedings - 2018 International Conference on Frontiers of Information Technology, FIT 2018

Conference

Conference16th International Conference on Frontiers of Information Technology, FIT 2018
CountryPakistan
CityIslamabad
Period12/17/1812/19/18

Keywords

  • Attack Surface
  • Attacks
  • Autonomous Vehicle
  • Deep Learning
  • DNNs
  • Machine Learning
  • Neural Networks
  • Security
  • Traffic Sign Detection

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Control and Optimization
  • Modeling and Simulation
  • Social Sciences (miscellaneous)
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Security for machine learning-based systems: Attacks and challenges during training and inference'. Together they form a unique fingerprint.

Cite this