SoK: Attack and Defense Landscape of Mobile On-device AI Systems
2026-07-01 • Cryptography and Security
Cryptography and SecurityArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors explain that mobile on-device AI (MoAI) systems run AI models directly on users' devices instead of in the cloud, which helps protect privacy, reduce delays, and work without internet. However, storing AI models locally creates new security risks. They review what is known about MoAI security, including possible attacks and defenses, and identify areas needing more research. Their work provides a clear framework to help others build safer MoAI systems in the future.
Mobile on-device AIAI securityPrivacy-preserving AIModel inferenceAttack landscapeDefense strategiesLocal AI modelsSystematization of knowledgeLatencyOffline capability
Authors
Yujin Huang, Xin Zheng, Xingliang Yuan, Kwok-Yan Lam
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.