ML Security PapersSWaRL: Safeguard Code Watermarking via Reinforcement Learning
Neusha Javidnia, Ruisi Zhang, Ashish Kundu et al. · University of California · Cisco Research
RL-trained LoRA adapters embed detectable watermarks in code LLM outputs, resisting refactoring and adversarial removal attacks
We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLM owners by embedding unique and verifiable signatures in the generated output. Existing approaches rely on manually crafted transformation rules to preserve watermarked code functionality or manipulate token-generation probabilities at inference time, which are prone to compilation errors. To address these challenges, SWaRL employs a reinforcement learning-based co-training framework that uses compiler feedback for functional correctness and a jointly trained confidential verifier as a reward signal to maintain watermark detectability. Furthermore, SWaRL employs low-rank adaptation (LoRA) during fine-tuning, allowing the learned watermark information to be transferable across model updates. Extensive experiments show that SWaRL achieves higher watermark detection accuracy compared to prior methods while fully maintaining watermarked code functionality. The LoRA-based signature embedding steers the base model to generate and solve code in a watermark-specific manner without significant computational overhead. Moreover, SWaRL exhibits strong resilience against refactoring and adversarial transformation attacks.