SoK: Attack and Defense Landscape of Mobile On-device AI Systems

2026-06-30

AI Summary

While on-device deployment of AI models on mobile platforms offers privacy preservation and low-latency inference, it introduces new security risks stemming from local storage, and existing research lacks a systematic framework to address these challenges. This work presents the first Systematization of Knowledge (SoK) study in this domain, establishing a comprehensive analytical framework that encompasses security pillars, attack surfaces, and defense mechanisms to fully characterize the threat landscape of on-device mobile AI systems. The study not only identifies critical research gaps and outlines promising future directions but also releases the first open-source repository dedicated to this area, thereby providing a foundational reference for designing security-aware mobile AI systems and guiding subsequent research efforts.

Abstract

Mobile on-device AI (MoAI) systems that integrate locally deployed AI models with conventional mobile software components are emerging as a key paradigm for delivering intelligent functionality directly on end-user devices. By moving inference from remote cloud services to the local mobile environment, such systems enable privacy-preserving, low-latency, and offline-capable AI functionality, yet introduce new security risks arising from the local storage of AI models. This paper presents the first comprehensive systematization of knowledge on MoAI security, covering security pillars, attack landscape, and defense landscape of MoAI systems. We further identify unresolved gaps in current attack and defense research and point to promising directions for future research in this emerging area. Our work establishes the first systematic framework for understanding the attack and defense landscapes of MoAI systems, serving as a foundation for building secure MoAI systems and advancing research in this critical domain. Companion resources are available at https://github.com/Jinxhy/Awesome-MoAI-Security.

Problem

• Mobile on-device AI
• Security
• Attack landscape
• Defense landscape
• AI model security

Innovation

• Mobile on-device AI
• Security Systematization
• Attack Landscape
• Defense Landscape
• Model Protection