Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes
For researchers and practitioners designing watermarking schemes for high-stakes generative AI, this work provides rigorous theoretical benchmarks that quantify unavoidable performance trade-offs.
The paper establishes fundamental trade-offs between false-alarm probability, detection error probability, distortion, and information rate in multi-bit watermarking of stochastic processes, providing matched theoretical bounds and empirical validation.
We study multi-bit watermarking for data generated by stochastic processes, where a hidden message is embedded during sampling and must be decodable by an authorized detector that possesses side information unavailable to unauthorized observers. In high-stakes deployments, a practical watermark must simultaneously control false alarms, preserve generation quality without distorting the output distribution, and support reliable multi-bit decoding. Satisfying all three goals at once inevitably creates fundamental trade-offs. We formulate watermark embedding as a distributional information-embedding problem and watermark detection as a multiple-hypothesis testing problem under distortion and rate constraints, leading to four fundamental metrics: false-alarm probability, detection error probability, distortion, and information rate. Within this information-theoretic framework, we derive matched converse and achievability bounds that characterize the optimal trade-offs and provide scheme-agnostic benchmarks for any watermarking method. For stationary ergodic stochastic processes, we further obtain matched asymptotic limits and connect them to the finite-sample regime. Finally, we present a reference watermarking construction satisfying our assumptions and empirically illustrating the predicted trade-offs.