License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.NG-RES.2022.1
URN: urn:nbn:de:0030-drops-161099
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2022/16109/
Go to the corresponding OASIcs Volume Portal


Buttazzo, Giorgio

Can We Trust AI-Powered Real-Time Embedded Systems? (Invited Paper)

pdf-format:
OASIcs-NG-RES-2022-1.pdf (2 MB)


Abstract

The excellent performance of deep neural networks and machine learning algorithms is pushing the industry to adopt such a technology in several application domains, including safety-critical ones, as self-driving vehicles, autonomous robots, and diagnosis support systems for medical applications. However, most of the AI methodologies available today have not been designed to work in safety-critical environments and several issues need to be solved, at different architecture levels, to make them trustworthy. This paper presents some of the major problems existing today in AI-powered embedded systems, highlighting possible solutions and research directions to support them, increasing their security, safety, and time predictability.

BibTeX - Entry

@InProceedings{buttazzo:OASIcs.NG-RES.2022.1,
  author =	{Buttazzo, Giorgio},
  title =	{{Can We Trust AI-Powered Real-Time Embedded Systems?}},
  booktitle =	{Third Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2022)},
  pages =	{1:1--1:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-221-1},
  ISSN =	{2190-6807},
  year =	{2022},
  volume =	{98},
  editor =	{Bertogna, Marko and Terraneo, Federico and Reghenzani, Federico},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16109},
  URN =		{urn:nbn:de:0030-drops-161099},
  doi =		{10.4230/OASIcs.NG-RES.2022.1},
  annote =	{Keywords: Real-Time Systems, Heterogeneous architectures, Trustworthy AI, Hypervisors, Deep learning, Adversarial attacks, FPGA acceleration, Mixed criticality systems}
}

Keywords: Real-Time Systems, Heterogeneous architectures, Trustworthy AI, Hypervisors, Deep learning, Adversarial attacks, FPGA acceleration, Mixed criticality systems
Collection: Third Workshop on Next Generation Real-Time Embedded Systems (NG-RES 2022)
Issue Date: 2022
Date of publication: 11.06.2022


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI