Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection

Alexander Loth, Dominique Conceicao Rosario, Peter Ebinger, Martin Kappes, Marc-Oliver Pahl

TL;DR

The paper addresses the problem of verifying the authenticity of visual content amid the rise of generative AI, proposing a mobile, privacy-first framework that performs on-device provenance verification and AI-detection. It introduces a defense-in-depth pipeline combining cryptographic C2PA verification, heuristic metadata, watermark signals, and optional contextual checks to provide graded confidence at consumption time. The authors implement a Rust core with a Flutter frontend to deliver memory-safe, on-device processing and report regulatory-aligned features for EU AI Act and DSA compliance. The results show sub-second verification latency on modern iOS devices and discuss open challenges and future directions, including privacy-preserving techniques and cross-jurisdiction standards.

Abstract

The proliferation of generative AI poses challenges for information integrity assurance, requiring systems that connect model governance with end-user verification. We present Origin Lens, a privacy-first mobile framework that targets visual disinformation through a layered verification architecture. Unlike server-side detection systems, Origin Lens performs cryptographic image provenance verification and AI detection locally on the device via a Rust/Flutter hybrid architecture. Our system integrates multiple signals - including cryptographic provenance, generative model fingerprints, and optional retrieval-augmented verification - to provide users with graded confidence indicators at the point of consumption. We discuss the framework's alignment with regulatory requirements (EU AI Act, DSA) and its role in verification infrastructure that complements platform-level mechanisms.

Origin Lens: A Privacy-First Mobile Framework for Cryptographic Image Provenance and AI Detection

TL;DR

The paper addresses the problem of verifying the authenticity of visual content amid the rise of generative AI, proposing a mobile, privacy-first framework that performs on-device provenance verification and AI-detection. It introduces a defense-in-depth pipeline combining cryptographic C2PA verification, heuristic metadata, watermark signals, and optional contextual checks to provide graded confidence at consumption time. The authors implement a Rust core with a Flutter frontend to deliver memory-safe, on-device processing and report regulatory-aligned features for EU AI Act and DSA compliance. The results show sub-second verification latency on modern iOS devices and discuss open challenges and future directions, including privacy-preserving techniques and cross-jurisdiction standards.

Abstract

The proliferation of generative AI poses challenges for information integrity assurance, requiring systems that connect model governance with end-user verification. We present Origin Lens, a privacy-first mobile framework that targets visual disinformation through a layered verification architecture. Unlike server-side detection systems, Origin Lens performs cryptographic image provenance verification and AI detection locally on the device via a Rust/Flutter hybrid architecture. Our system integrates multiple signals - including cryptographic provenance, generative model fingerprints, and optional retrieval-augmented verification - to provide users with graded confidence indicators at the point of consumption. We discuss the framework's alignment with regulatory requirements (EU AI Act, DSA) and its role in verification infrastructure that complements platform-level mechanisms.
Paper Structure (13 sections, 6 figures, 2 tables)

This paper contains 13 sections, 6 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Architecture
  4. Security & Threat Modeling
  5. Evaluation & Discussion
  6. Conclusion and Future Directions
  7. Defense-in-Depth Verification Pipeline
  8. C2PA Manifest Structure
  9. System Architecture Details
  10. Analysis Workflow
  11. Verification Status Indicators
  12. Regulatory Alignment
  13. User Interface Screenshots

Figures (6)

  • Figure 1: Origin Lens architecture: Flutter UI, verification pipeline, FFI bridge, and Rust core. Cryptographic operations execute on-device below the processing boundary.
  • Figure S1: Defense-in-depth verification layers. Primary layers (top) provide highest confidence; lower layers offer fallback signals when cryptographic provenance is unavailable.
  • Figure S2: C2PA manifest structure showing the relationship between assertions, claims, cryptographic signatures, and content hash bindings.
  • Figure S3: Origin Lens hybrid architecture. The FFI boundary separates managed Dart code from native Rust, enabling memory-safe cryptographic operations.
  • Figure S4: Image analysis workflow showing decision points and four possible verification outcomes.
  • ...and 1 more figures