Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Instance-Specific watermarking with Two-Sided detection (ISTS), a novel watermarking paradigm for text-to-image diffusion models designed to improve robustness against removal and forgery attacks. ISTS dynamically adjusts watermark injection timing and patterns based on user prompt semantics. The proposed two-sided detection approach further enhances watermark detection robustness, demonstrating superior performance against adversarial attacks compared to existing methods.
Dynamically adjusting watermarks based on user prompts makes text-to-image diffusion models far more resilient to removal and forgery attacks.
Generated contents have raised serious concerns about copyright protection, image provenance, and credit attribution. A potential solution for these problems is watermarking. Recently, content watermarking for text-to-image diffusion models has been studied extensively for its effective detection utility and robustness. However, these watermarking techniques are vulnerable to potential adversarial attacks, such as removal attacks and forgery attacks. In this paper, we build a novel watermarking paradigm called Instance-Specific watermarking with Two-Sided detection (ISTS) to resist removal and forgery attacks. Specifically, we introduce a strategy that dynamically controls the injection time and watermarking patterns based on the semantics of users'prompts. Furthermore, we propose a new two-sided detection approach to enhance robustness in watermark detection. Experiments have demonstrated the superiority of our watermarking against removal and forgery attacks.