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

Authors: Shail Dave, Alberto Marchisio, Muhammad Abdullah Hanif, Amira Guesmi, Aviral Shrivastava, Ihsen Alouani, Muhammad Shafique
Published: 2022-04-18

Source: https://arxiv.org/abs/2204.09514

PDF: https://arxiv.org/pdf/2204.09514

AIにより推定されたラベル

防御手法 バックドア攻撃 メンバーシップ推論

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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.