Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben

2023 | Buch

Introduction to Machine Learning for Hardware Security Kapitel lesen Erstes Kapitel lesen

Deep Learning for Computational Problems in Hardware Security

Modeling Attacks on Strong Physically Unclonable Function Circuits

verfasst von: Pranesh Santikellur, Rajat Subhra Chakraborty

Verlag: Springer Nature Singapore

Buchreihe : Studies in Computational Intelligence

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten
insite
SUCHEN

Über dieses Buch

The book discusses a broad overview of traditional machine learning methods and state-of-the-art deep learning practices for hardware security applications, in particular the techniques of launching potent "modeling attacks" on Physically Unclonable Function (PUF) circuits, which are promising hardware security primitives. The volume is self-contained and includes a comprehensive background on PUF circuits, and the necessary mathematical foundation of traditional and advanced machine learning techniques such as support vector machines, logistic regression, neural networks, and deep learning. This book can be used as a self-learning resource for researchers and practitioners of hardware security, and will also be suitable for graduate-level courses on hardware security and application of machine learning in hardware security. A stand-out feature of the book is the availability of reference software code and datasets to replicate the experiments described in the book.

Inhaltsverzeichnis

Frontmatter
Chapter 1. Introduction to Machine Learning for Hardware Security
Abstract
Computing devices have become the basis of our modern lives, and hardware has long been considered as the backbone of trust for all computing systems. Various software attacks and defense mechanisms, mainly based on cryptographic measures, have been widely analyzed and applied in a variety of applications. In comparison to software security, hardware security as a topic is relatively new, and its importance has drastically increased in recent years due to the multiple attacks on hardware that were thought to be immune to attack. Hardware security is no different than any other field of security that focuses on launching attacks to steal assets and on strategies designed to protect them. In particular, the topic of hardware security is focused on situations where the assets are hardware components that contain secrets of electronic components, such as cryptographic keys and other sensitive information [1].
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 2. Physically Unclonable Functions
Abstract
Physically Unclonable Functions (PUFs) are promising hardware security primitives which can be useful in implementing lightweight authentication protocols without the need for explicit key storage. PUFs are electronic circuits that manifest the impact of nanoscale process variation induced randomness of modern semiconductor manufacturing technology [1, 2]. Each individual PUF instance should have unique characteristics, which should clearly distinguish it from other instances of the same PUF family. Typically, this unique characteristic is in the form of the truth-table for a given PUF instance, and an n-bit input, m-bit output PUF instance can be mathematically represented as a Boolean function \(f\!: \{0,1\}^n \rightarrow \{0,1\}^m\).
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 3. Machine-Learning Basics
Abstract
In Chap. 1, we discussed how machine-learning algorithms differ from traditional algorithms. This chapter will introduce some machine-learning terminologies as well as some details about the working of ML algorithms.
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 4. Modeling Attacks on PUF
Abstract
Modeling attacks are considered to be the greatest threat against strong PUF implementations, and wide-ranging intensive research is currently underway to develop newer attacks.
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 5. Improved Modeling Attack on PUFs based on Tensor Regression Network
Abstract
In the previous chapter, we have discussed DFNN-based modeling attacks on various APUF compositions. The purpose of this chapter is to understand design and development of an improved machine learning model for launching modeling attacks.
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 6. Combinational Logic-Based Implementation of PUF
Abstract
In the earlier chapters, we have noted that a standalone arbiter PUF is vulnerable to machine learning (ML) attacks; however, multiple instances of arbiter PUF can be combined to create more robust PUF variants.
Pranesh Santikellur, Rajat Subhra Chakraborty
Chapter 7. Conclusion
Abstract
We have focused on applications of machine learning in the domain of hardware security, with a particular cover on modeling attacks against PUFs in this book. In the first chapter, we have introduced briefly popular hardware-based attacks and countermeasures.
Pranesh Santikellur, Rajat Subhra Chakraborty
Metadaten
Titel
Deep Learning for Computational Problems in Hardware Security
verfasst von
Pranesh Santikellur
Rajat Subhra Chakraborty
Copyright-Jahr
2023
Verlag
Springer Nature Singapore
Electronic ISBN
978-981-19-4017-0
Print ISBN
978-981-19-4016-3
DOI
https://doi.org/10.1007/978-981-19-4017-0

Neuer Inhalt

    Bildnachweise