본문 바로가기
  • Home

A Study on Hardware-Based Content Provenance Authentication Framework for On-Device AI

  • Journal of Software Forensics
  • Abbr : JSAV
  • 2026, 22(1), pp.31~40
  • Publisher : Korea Software Assessment and Valuation Society
  • Research Area : Engineering > Computer Science
  • Received : March 11, 2026
  • Accepted : March 20, 2026
  • Published : March 31, 2026

Su-Hong Shin 1 Byoungsoo Koh 2

1디지캡
2한신대

Accredited

ABSTRACT

The proliferation of generative AI and on-device AI has enabled edge devices such as smartphones, smart glasses, and IoT devices to generate, capture, and edit content locally. However, software-based security mechanisms face structural limitations including OS-level bypass risks, cryptographic overhead under constrained resources, and offline authentication gaps. This study proposes HW-CPA (Hardware-based Content Provenance Authentication), a hardware-oriented framework comprising four layers: NPU-based content classification, TEE-based C2PA manifest generation, Hardware Root of Trust-based device identity assurance, and offline hash chain-based deferred verification. Threat modeling, commercial technology mapping, and a software emulation prototype confirm consistent tamper detection and acceptable signing/verification latency for consumer-grade environments. This work provides a foundation for future SoC-level integration toward trustworthy generative AI content.

Citation status

* References for papers published after 2024 are currently being built.