arXiv:2607.00362v1 Announce Type: cross 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 M
The proliferation of on-device AI necessitates a comprehensive understanding of its security vulnerabilities, making this a critical area of research as adoption accelerates.
Sophisticated readers should care about this as it highlights emerging security risks in a key area of AI deployment, impacting privacy, device integrity, and user trust.
This report systematizes the attack and defense landscape for mobile on-device AI, providing a foundational reference for developers, security researchers, and policymakers.
- · Cybersecurity firms
- · Mobile OS developers
- · AI model developers
- · Privacy-focused tech companies
- · Unsecured mobile AI applications
- · Users unknowingly exposed to vulnerabilities
- · Cloud AI service providers (in some use cases)
Increased focus on robust security frameworks for edge AI deployments will emerge.
New regulatory pressures may arise to mandate security standards for AI integrated into consumer devices.
The development of adversarial AI techniques specifically targeting mobile on-device models could become a significant cybersecurity threat.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG