Table of Contents
Fetching ...

Explainability as a Requirement for Hardware: Introducing Explainable Hardware (XHW)

Timo Speith, Julian Speith, Steffen Becker, Yixin Zou, Asia Biega, Christof Paar

TL;DR

Hardware opacity poses security and trust challenges in modern systems. The authors introduce Explainable Hardware (XHW) and a stakeholder-centered framework that connects desiderata to concrete explainability approaches, grounded by an exploratory survey with 18 hardware experts. They identify gaps, particularly for end users and regulatory alignment, and propose future research directions including hardware labels, adapting XAI techniques to hardware, and supporting the right to repair. This work lays a foundation for integrating hardware explainability into requirements engineering, policy discussions, and design practices to foster trustworthy, repairable, and transparent hardware systems.

Abstract

In today's age of digital technology, ethical concerns regarding computing systems are increasing. While the focus of such concerns currently is on requirements for software, this article spotlights the hardware domain, specifically microchips. For example, the opaqueness of modern microchips raises security issues, as malicious actors can manipulate them, jeopardizing system integrity. As a consequence, governments invest substantially to facilitate a secure microchip supply chain. To combat the opaqueness of hardware, this article introduces the concept of Explainable Hardware (XHW). Inspired by and building on previous work on Explainable AI (XAI) and explainable software systems, we develop a framework for achieving XHW comprising relevant stakeholders, requirements they might have concerning hardware, and possible explainability approaches to meet these requirements. Through an exploratory survey among 18 hardware experts, we showcase applications of the framework and discover potential research gaps. Our work lays the foundation for future work and structured debates on XHW.

Explainability as a Requirement for Hardware: Introducing Explainable Hardware (XHW)

TL;DR

Hardware opacity poses security and trust challenges in modern systems. The authors introduce Explainable Hardware (XHW) and a stakeholder-centered framework that connects desiderata to concrete explainability approaches, grounded by an exploratory survey with 18 hardware experts. They identify gaps, particularly for end users and regulatory alignment, and propose future research directions including hardware labels, adapting XAI techniques to hardware, and supporting the right to repair. This work lays a foundation for integrating hardware explainability into requirements engineering, policy discussions, and design practices to foster trustworthy, repairable, and transparent hardware systems.

Abstract

In today's age of digital technology, ethical concerns regarding computing systems are increasing. While the focus of such concerns currently is on requirements for software, this article spotlights the hardware domain, specifically microchips. For example, the opaqueness of modern microchips raises security issues, as malicious actors can manipulate them, jeopardizing system integrity. As a consequence, governments invest substantially to facilitate a secure microchip supply chain. To combat the opaqueness of hardware, this article introduces the concept of Explainable Hardware (XHW). Inspired by and building on previous work on Explainable AI (XAI) and explainable software systems, we develop a framework for achieving XHW comprising relevant stakeholders, requirements they might have concerning hardware, and possible explainability approaches to meet these requirements. Through an exploratory survey among 18 hardware experts, we showcase applications of the framework and discover potential research gaps. Our work lays the foundation for future work and structured debates on XHW.
Paper Structure (27 sections, 6 figures, 3 tables)

This paper contains 27 sections, 6 figures, 3 tables.

Figures (6)

  • Figure 1: A simplified version of the explainability models that Langer et al. Langer2021What and Hofmann et al. Hoffman2018Metrics have proposed.
  • Figure 2: Our XHW Framework: Stakeholders want 1 desiderata and can use 2 explainability approaches that contribute to 3 satisfying these desiderata.
  • Figure 3: Stakeholder interactions among each other, with the hardware, and with the system as a whole.
  • Figure 4: Mean values of participants' responses on the perceived importance of individual desiderata for each stakeholder on a scale from "1 -- not at all important" to "5 -- extremely important".
  • Figure 5: Mean values of participants' responses on the applicability of existing explainability approaches for each stakeholder category on a scale from "1 -- not at all applicable" to "5 -- extremely applicable".
  • ...and 1 more figures

Theorems & Definitions (2)

  • Definition 1: System Explainability
  • Definition 2: Trustworthiness