Cross-Model Watermarking via Discriminative Samples for Secure Authentication

摘要

Deep neural networks on cloud platforms face growing security threats, with AI services increasingly relying on heterogeneous models for the same task to meet diverse user needs. Existing methods fail to distinguish benign modifications from malicious attacks in cross-model scenarios. To address this challenge, we propose a non-intrusive cross-model watermarking method that generates discriminative samples as universal keys, enabling authentication without altering model parameters or architectures. Specifically, we introduce a margin enhancement loss to amplify confidence gaps between benign and malicious behaviors, ensuring high transferability across models. Both theoretical analysis and experimental results demonstrate the high efficacy of our proposed method. The generated samples maintain high visual fidelity (SSIM > 0.99), achieve over 3 times higher discriminability than existing methods, retain over 93% accuracy under benign modifications, and detect malicious attacks with accuracy dropping below 9%. Overall, our proposed method provides a robust, transferable, and non-intrusive solution for cross-model authentication, making it ideal for real-world applications where security is critical.