Record link: 
http://hdl.handle.net/20.500.12708/142205
-
Title: 
Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems
en
Citation: 
Dave, S., Marchisio, A., Hanif, M. A., Guesmi, A., Shrivastava, A., Alouani, I., & Shafique, M. (2022). Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems. In Proceedings 2022 IEEE 40th VLSI Test Symposium (VTS) (pp. 1–14). https://doi.org/10.1109/VTS52500.2021.9794253
-
Publisher DOI: 
10.1109/VTS52500.2021.9794253
-
Publication Type: 
Inproceedings - Full-Paper Contribution
en
Language: 
English
-
Authors: 
Dave, Shail 
Marchisio, Alberto 
Hanif, Muhammad Abdullah 
Guesmi, Amira 
Shrivastava, Aviral 
Alouani, Ihsen 
Shafique, Muhammad 
-
Organisational Unit: 
E191-02 - Forschungsbereich Embedded Computing Systems 
-
Published in: 
Proceedings 2022 IEEE 40th VLSI Test Symposium (VTS) 
-
ISBN: 
978-1-6654-1060-1
-
Volume: 
2022-April
-
Date (published): 
2022
-
Event name: 
2022 IEEE 40th VLSI Test Symposium (VTS) 
en
Event date: 
25-Apr-2022 - 27-Apr-2022
-
Event place: 
United States of America (the)
-
Number of Pages: 
14
-
Keywords: 
Agility; Codesign; DNN; Energy efficiency; ML; Neural Networks; Performance; Privacy; Reliability; Robustness; Security
en
Abstract: 
The real-world use cases of Machine Learning (ML) have exploded over the past few years. However, the current computing infrastructure is insufficient to support all real-world applications and scenarios. Apart from high efficiency requirements, modern ML systems are expected to be highly reliable against hardware failures as well as secure against adversarial and IP stealing attacks. Privacy concerns are also becoming a first-order issue. This article summarizes the main challenges in agile development of efficient, reliable and secure ML systems, and then presents an outline of an agile design methodology to generate efficient, reliable and secure ML systems based on user-defined constraints and objectives.
en
Research Areas: 
Computer Engineering and Software-Intensive Systems: 100%
-
Science Branch: 
1020 - Informatik: 100%
-
Appears in Collections:
Conference Paper

Show full item record

Google ScholarTM

Check