SoK: Towards Security and Safety of Edge AI

TL;DR

This paper surveys the security and safety challenges of Edge AI, emphasizing their importance and the need for integrated solutions, while summarizing existing threats and countermeasures to guide future research.

Contribution

It provides a comprehensive survey of security and safety issues in Edge AI, highlighting open challenges and proposing directions for future research.

Findings

Identified key security threats in Edge AI

Summarized existing countermeasures

Outlined open challenges for future work

Abstract

Advanced AI applications have become increasingly available to a broad audience, e.g., as centrally managed large language models (LLMs). Such centralization is both a risk and a performance bottleneck - Edge AI promises to be a solution to these problems. However, its decentralized approach raises additional challenges regarding security and safety. In this paper, we argue that both of these aspects are critical for Edge AI, and even more so, their integration. Concretely, we survey security and safety threats, summarize existing countermeasures, and collect open challenges as a call for more research in this area.