eprint.iacr.orgpaperConfidential Error-Correcting Codes
Introduces Confidential Error-correcting Codes (CECs), a cryptographic primitive for decoding perturbed codewords while keeping the message confidential, defined by confidentiality, robustness and soundness. The Randomness-Security Separation framework encodes a nonce and masks the payload with a PRF. The Conc-CEC instantiation uses concatenated Reed-Muller and Reed-Solomon codes, and the authors claim stronger concrete security than PRCs (CRYPTO'24). The CECMark application watermarks AI-generated images, and the authors report it beats Gaussian Shading, PRCMark and T2SMark across 56 perturbations with a false positive rate below 10^-5.
TL;DR New provably secure error-correcting-code primitive (PRF-masked Reed-Muller/Reed-Solomon) used for robust AI image watermarking that outperforms PRCMark and Gaussian Shading.
Also seen from another angle🧠 AI →
Organisations named here
- CECMark
- Conc-CEC
- Gaussian Shading
- PRCMark
- Randomness-Security Separation
- T2SMark
Technologies named here
- Conc-CEC
- CECMark
- Gaussian Shading
- PRCMark
- T2SMark
- PRCs
Techniques named here
- Randomness-Security Separation framework
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle