Confidential error correcting codes enable reliable private watermarking
Confidential Error-Correcting Codes
Cryptography and Security
Summary
Sometimes digital messages get changed or damaged during transmission, so error-correcting codes help fix these mistakes. The authors propose confidential error-correcting codes (CECs) that not only fix errors but also keep the original message secret. They design CECs using a technique that mixes randomness and masking to ensure security and reliability. They apply this idea to watermark AI-generated images, making the watermarks robust against many changes while keeping false detections very rare.
What this means in practice
- •For digital content creators: Embed robust, confidential watermarks into AI-generated images that survive many edits and avoid false detections.
- •For network security engineers: Improve secure communication systems by integrating error correction that also preserves message confidentiality under realistic conditions.
Authors
Tianrui Wang, Anyu Wang, Tianshuo Cong, Delong Ran, Xiaoyun Wang
Abstract
We introduce Confidential Error-correcting Codes (CECs), a new cryptographic primitive that enables reliable decoding from perturbed codewords while preserving message confidentiality. We formalize this primitive through three security properties: confidentiality, robustness, and soundness. To realize this goal, we develop a general framework for constructing CECs based on a Randomness-Security Separation (RSS) structure, which first encodes a nonce to introduce randomness and then masks the encoded payload with a pseudorandom function. Based on our RSS framework, we instantiate CECs, called Conc-CEC, using concatenated Reed-Muller and Reed-Solomon codes. The resulting Conc-CEC admits provable guarantees for all three properties. Notably, compared to PRCs (CRYPTO'24), another recent cryptographic primitive with error-correcting capability, CECs achieve significantly stronger concrete security guarantees under practical parameter settings. As a primary application of CECs, we further present CECMark, a watermarking scheme for AI-generated images. Our experiments on real-world generative image models show that CECMark consistently outperforms state-of-the-art watermarking methods, including Gaussian Shading (CVPR'24), PRCMark (ICLR'25), and T2SMark (NeurIPS'25). In particular, CECMark achieves higher robustness across all 56 evaluated perturbations and ensures a false positive rate below $10^{-5}$ without introducing side effects. Taken together, our work lays a novel cryptographic foundation for trustworthy watermarking schemes that, for the first time, unify provable security guarantees with strong practical reliability.