The field of federated learning is moving towards increased focus on intellectual property protection, with a emphasis on developing robust watermarking techniques to prevent model theft and ensure ownership verification. Recent advances have introduced novel frameworks that achieve collision-free watermark aggregation, enhanced watermark security, and visually interpretable ownership verification. Additionally, researchers have identified new attack surfaces, such as compromising model interpretability through color perturbations, highlighting the need for more comprehensive security measures. Noteworthy papers include: FLClear, which proposes a novel framework for visually verifiable multi-client watermarking, and RISE, which introduces a robust client-server watermarking scheme for split federated learning. Sigil is also notable for its server-enforced watermarking framework designed for capability-limited servers, and the work on poisoning interpretability in federated learning via color skew highlights the vulnerability of model explanations to adversarial attacks.