VeriChroma: Ownership Verification for Federated Models via RGB Filters

The rapid evolution of artificial intelligence (AI), especially in deep learning, is significantly driven by big data. However, the intensive resources required for training deep neural networks (DNN) highlight the urgent need for effective model protection and ownership verification. Current neural network watermarking methods fall short in federated learning contexts. This paper introduces VeriChroma, an innovative framework crafted to secure DNN models and affirm ownership within such environments. VeriChroma enables clients to embed and verify private ID-based watermarks independently, ensuring straightforward ownership claims. Through strategic image blocking and positional mapping, it overcomes conflicts between client constraints, ensuring tailored watermark integration. Furthermore, VeriChroma utilizes RGB filters for watermark triggers, bolstering both the robustness and stealth of the watermarking process. Our findings underscore VeriChroma’s effectiveness and practicality, showcasing its potential to enhance DNN model security, resolve federated learning disputes, and provide secure, unobtrusive watermarking, marking a significant advancement in federated learning security and intellectual property rights protection.