ZK-WAGON: Imperceptible Watermark for Image Generation Models using ZK-SNARKs
This addresses authenticity and misuse risks for users of image generation models, though it is incremental as it builds on existing watermarking and ZK-SNARK techniques.
The paper tackles the problem of authenticating synthetic images by introducing ZK-WAGON, a system that uses ZK-SNARKs to embed imperceptible watermarks, enabling verifiable proof of origin without exposing model details and reducing proof generation time with Selective Layer ZK-Circuit Creation.
As image generation models grow increasingly powerful and accessible, concerns around authenticity, ownership, and misuse of synthetic media have become critical. The ability to generate lifelike images indistinguishable from real ones introduces risks such as misinformation, deepfakes, and intellectual property violations. Traditional watermarking methods either degrade image quality, are easily removed, or require access to confidential model internals - making them unsuitable for secure and scalable deployment. We are the first to introduce ZK-WAGON, a novel system for watermarking image generation models using the Zero-Knowledge Succinct Non Interactive Argument of Knowledge (ZK-SNARKs). Our approach enables verifiable proof of origin without exposing model weights, generation prompts, or any sensitive internal information. We propose Selective Layer ZK-Circuit Creation (SL-ZKCC), a method to selectively convert key layers of an image generation model into a circuit, reducing proof generation time significantly. Generated ZK-SNARK proofs are imperceptibly embedded into a generated image via Least Significant Bit (LSB) steganography. We demonstrate this system on both GAN and Diffusion models, providing a secure, model-agnostic pipeline for trustworthy AI image generation.