Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems

Résumé

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.
Fichier principal
Vignette du fichier
Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems.pdf (1.68 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03796590 , version 1 (25-05-2023)

Identifiants

Citer

Shail Dave, Alberto Marchisio, Muhammad Abdullah Hanif, Amira Guesmi, Aviral Shrivastava, et al.. Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems: Special Session. 2022 IEEE 40th VLSI Test Symposium (VTS), Apr 2022, San Diego, United States. pp.1-14, ⟨10.1109/VTS52500.2021.9794253⟩. ⟨hal-03796590⟩
41 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More