zk-REAL: A Zero-Knowledge-Based Protocol for Repeated Image Edit Authenticity Proof With Lattice Hashing
Atsuki Koyama, Kentaroh Toyoda, Manato Fujimoto, Thi Hong Tran · IEEE Open Journal of the Computer Society · 2026
The rapid advancement of deepfake technology poses risks, including financial fraud and political misinforma tion, demanding robust methods for verifying image content authenticity. While C2PA and ZK-based methods provide mechanisms for authenticity, existing solutions struggle to efficiently support privacy-preserving edits and iterative modifications. We present zk-REAL, a system that combines lattice-based hashing (LHF) with a Halo2 circuit design to reduce constraint cost and to exploit LHF updatability for partial recomputation after local edits. To remain interoperable with standard toolchains, a SHA 256 hash is computed outside the circuit as a compatibility layer with C2PA. On 720p images, our implementation demonstrates reduced key-generation cost (2× faster) and proving time for complex transformations. For repeated edits we achieve up to 29% proving-time reduction relative to recomputing from scratch, and 48% for double-edit contrast. Trade-offs include larger proof sizes for simple operations (crop, resize) versus smaller proofs for complex operations (contrast), indicating suitability for computationally intensive multi-edit workflows.