Securing XAI through Trusted Computing
Year: 2024
Type: conference-paper
Abstract: The escalating use of Artificial Intelligence (AI) and Machine Learning (ML) systems underscores the need for transparency and data security. This paper explores the fusion of Explainable AI (XAI) with trusted computing technologies such as Trusted Platform Modules (TPMs) and Trusted Execution Environments (TEEs). Highlighting the synergy etween XAI, aimed at elucidating ML decision-making, and trusted computing, which fortifies system integrity, this study introduces novel approaches. Specifically, it proposes leveraging TEEs to protect user privacy during XAI computation and TPMs to verify system trustworthiness. This integration seeks to augment trust in AI systems by securing personal data processing and ensuring system integrity, thereby potentially reshaping the landscape of trust in AI technologies.
Author: Maximilian Becker
Language: English
Subfield: Hardware and Architecture
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4411037656
