@inproceedings{94bfd7614d954161b7349fe3f9c41ea0,
title = "Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems",
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.",
keywords = "Agility, Codesign, DNN, Energy efficiency, ML, Neural Networks, Performance, Privacy, Reliability, Robustness, Security",
author = "Shail Dave and Alberto Marchisio and Hanif, {Muhammad Abdullah} and Amira Guesmi and Aviral Shrivastava and Ihsen Alouani and Muhammad Shafique",
note = "Funding Information: At ASU, this work was supported in part by NSF under Grant CCF 1723476 NSF/Intel Joint Research Center for Computer Assisted Programming for Heterogeneous Architectures (CAPA). At TU Wien, this work has been supported in part by Intel Corporation through Gift funding for the project {"}Cost-Effective Dependability for Deep Neural Networks and Spiking Neural Networks{"}, and by the Doctoral College Resilient Embedded Systems, which is run jointly by the TU Wien s Faculty of Informatics and the UAS Technikum Wien. At NYUAD, different parts of these works were also supported in parts by the NYUAD Center for Interacting Urban Networks (CITIES), funded by Tamkeen under the NYUAD Research Institute Award CG001, Center for CyberSecurity (CCS), funded by Tamkeen under the NYUAD Research Institute Award G1104, and Center for Artificial Intelligence and Robotics (CAIR), funded by Tamkeen under the NYUAD Research Institute Award CG010. At UPHF, this work has been supported in part by RESIST project funded by R egion Hauts-de-France through STIMULE scheme (AR 21006614). Funding Information: ACKNOWLEDGMENT At ASU, this work was supported in part by NSF under Grant CCF 1723476—NSF/Intel Joint Research Center for Computer Assisted Programming for Heterogeneous Architectures (CAPA). At TU Wien, this work has been supported in part by Intel Corporation through Gift funding for the project “Cost-Effective Dependability for Deep Neural Networks and Spiking Neural Networks”, and by the Doctoral College Resilient Embedded Systems, which is run jointly by the TU Wien{\textquoteright}s Faculty of Informatics and the UAS Technikum Wien. At NYUAD, different parts of these works were also supported in parts by the NYUAD Center for Interacting Urban Networks (CITIES), funded by Tamkeen under the NYUAD Research Institute Award CG001, Center for CyberSecurity (CCS), funded by Tamkeen under the NYUAD Research Institute Award G1104, and Center for Artificial Intelligence and Robotics (CAIR), funded by Tamkeen under the NYUAD Research Institute Award CG010. At UPHF, this work has been supported in part by RESIST project funded by R{\'e}gion Hauts-de-France through STIMULE scheme (AR 21006614). Publisher Copyright: {\textcopyright} 2022 IEEE.; 40th IEEE VLSI Test Symposium, VTS 2022 ; Conference date: 25-04-2022 Through 27-04-2022",
year = "2022",
doi = "10.1109/VTS52500.2021.9794253",
language = "English (US)",
series = "Proceedings of the IEEE VLSI Test Symposium",
publisher = "IEEE Computer Society",
booktitle = "Proceedings - 2022 IEEE 40th VLSI Test Symposium, VTS 2022",
}