Book section Embargoed Access

Robust Computing for Machine Learning-Based Systems

Muhammad Abdullah Hanif; Faiq Khalid; Rachmad Vidya Wicaksana Putra; Mohammad Taghi Teimoori; Florian Kriebel; Jeff (Jun) Zhang; Kang Liu; Semeen Rehman; Theocharis Theocharides; Alessandro Artusi; Siddharth Garg; Muhammad Shafique

The drive for automation and constant monitoring has led to rapid development in the field of Machine Learning (ML). The high accuracy offered by the state-of-the-art ML algorithms like Deep Neural Networks (DNNs) has paved the way for these algorithms to being used even in the emerging safety-critical applications, e.g., autonomous driving and smart healthcare. However, these applications require assurance about the functionality of the underlying systems/algorithms. Therefore, the robustness of these ML algorithms to different reliability and security threats has to be thoroughly studied and mechanisms/methodologies have to be designed which result in increased inherent resilience of these ML algorithms. Since traditional reliability measures like spatial and temporal redundancy are costly, they may not be feasible for DNN-based ML systems which are already super compute and memory intensive. Hence, new robustness methods for ML systems are required. Towards this, in this chapter, we present our analyses illustrating the impact of different reliability and security vulnerabilities on the accuracy of DNNs. We also discuss techniques that can be employed to design ML algorithms such that they are inherently resilient to reliability and security threats. Towards the end, the chapter provides open research challenges and further research opportunities.

 

This work has been partly supported by the project that has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 739578 (RISE – Call: H2020-WIDESPREAD-01-2016-2017-TeamingPhase2) and the Government of the Republic of Cyprus through the Directorate General for European Programmes, Coordination and Development.
Embargoed Access

Files are currently under embargo but will be publicly accessible after December 10, 2022.

12
3
views
downloads
Views 12
Downloads 3
Data volume 32.6 MB
Unique views 11
Unique downloads 3

Share

Cite as