Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms

M Anjan Kumar; Kishor Kumar Gajula; Ch Prathima

cs.CRAug 1, 2026

Secure AI Watermarking Framework for IP Protection in Multi-Tenant Cloud Platforms

Authors: M Anjan Kumar, Kishor Kumar Gajula, Ch Prathima

Organizations: Department of Computer Science and Engineering , Viswam Engineering College, Madanapalle, Andhra Pradesh , India · Department of Computer Science and Engineering , Mother Theresa Institute Of Engineering and Technology, Peddapalli, Telangana, India · Department of Computer Science and Engineering , Mohan Babu University, Tirupathi, Andhra Pradesh ; India

Abstract

The Secured data safe guard transaction with multi-tenant environments run on private-protected authenticate platforms runs by secured handed environments that emerges with the expansion of cloud-based AI services. To enhanced this secured leakage address challenges solution to protect a secure AI Watermarking system incorporating key distributed between trusted parties based on key authentication as we proposed solution to guided safe guarded way to reactive, and proactive security alert systems using algorithms. This proposed system before attacks can be prevented through the active measures. domain run base restrictions with limited access. Conversely, Proposed system reactive methods to captured on watermarking and biometric identification owner device specific IP leakage that occur during the exchange of data and models in federated and remote learning algorithms.

Explore similar work

Attribute-based Undetectable Watermarking for Generative AI Models
Aug 4, 2026Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel +1Watermarking Watermarks
Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection
May 22, 2026Kieu Dang, Phung Lai, NhatHai Phan +2Large Language Model Watermarks Watermarking
FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs
Jun 22, 2026Wenlong Cheng, Yuan Gan, Yunqiu Xu +1Federated Learning Watermarks

Aug 4, 2026 · cs.CRJ/K move · Enter open · S save

Attribute-based Undetectable Watermarking for Generative AI Models

Miryam Mi-Ying Huang, Chung-Wei Lee, Max Raffel, Er-Cheng Tang

Carnegie Mellon University Pittsburgh, PA, USA · Independent Researcher · University of Southern California Los Angeles, CA, USA · University of Washington Seattle, WA, USA

Generative AI systems increasingly produce content whose provenance is difficult to verify, motivating watermarking techniques for identifying model-generated outputs. Existing cryptographic watermarking methods provide strong undetectability guarantees: without a detection key, watermarked outputs are computationally indistinguishable from unwatermarked ones. However, these approaches do not address the crucial deployment challenge of how to safely delegate detection capabilities. With an unrestricted detection key, a malicious detector may use the detection key beyond its intended scope, enabling watermark sanitization, scope abuse, and user profiling. To mitigate this safety concern, we introduce, to the best of our knowledge, the first \emph{attribute-based watermarking} for generative AI models, providing fine-grained, policy-controlled watermark detection. In our approach, each generated output is associated with attributes, and each detection key is \emph{constrained by a policy} on potential attributes. A detection key can only be used to detect watermarked outputs whose attributes satisfy the corresponding policy, while watermarked outputs that fall outside the policy remain computationally indistinguishable from unwatermarked ones. We construct such an attribute-based watermarking scheme and formalize its security properties, including consistency, adaptive robustness to bounded corruptions, undetectability, and soundness, along with a security proof under standard cryptographic assumptions. Our construction integrates constrained pseudorandom functions, pseudorandom error-correcting codes, and randomness recovery procedures with generative AI models. Finally, we implement a prototype and an empirical evaluation, demonstrating that attribute-based watermarking is both effective and practical.

Watermarking Watermarks Generative Artificial Intelligence

Open paper Ask about it PDF

Abstract

Explore similar work

Attribute-based Undetectable Watermarking for Generative AI Models

Robust LLM Watermarking with Minimal Semantic Distortion for IP Protection

FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs