Deep learning-based remote sensing object detection (RSOD) models have been widely deployed and commercialized. The commercialization of RSOD models requires the ability to protect their intellectual property (IP) across different platforms and sales channels. However, RSOD models currently face threats related to illegal copying on untrusted platforms or resale by dishonest buyers. To address this issue, we propose a dual-model watermarking scheme for the copyright verification and leakage tracing of RSOD models. First, we construct trigger samples using an object generation watermark trigger and train them alongside clean samples to implement black-box watermarking. Then, fingerprint information is embedded into a small subset of the model’s critical weights, using a fine-tuning and loss-guided approach. At the copyright verification stage, the presence of a black-box watermark can be confirmed through using the suspect model’s API to make predictions on the trigger samples, thereby determining whether the model is infringing. Once infringement is confirmed, fingerprint information can be further extracted from the model weights to identify the leakage source. Experimental results demonstrate that the proposed method can effectively achieve the copyright verification and traceability of RSOD models without affecting the performance of primary tasks. The watermark shows good robustness against fine-tuning and pruning attacks.
High-quality datasets are essential for training high-performance models, while the process of collection, cleaning, and labeling is costly. As a result, datasets are considered valuable intellectual property. However, when security mechanisms are symmetry-breaking, creating exploitable vulnerabilities, unauthorized use or data leakage can infringe on the copyright of dataset owners. In this study, we design a method to mount clean-label dataset watermarking based on trigger optimization, aiming to protect the copyright of the dataset from infringement. We first perform iterative optimization of the trigger based on a surrogate model, with targets class samples guiding the updates. The process ensures that the optimized triggers contain robust feature representations of the watermark target class. A watermarked dataset is obtained by embedding optimized triggers into randomly selected samples from the watermark target class. If an adversary trains a model with the watermarked dataset, our watermark will manipulate the model’s output. By observing the output of the suspect model on samples with triggers, it can be determined whether the model was trained on the watermarked dataset. The experimental results demonstrate that the proposed method exhibits high imperceptibility and strong robustness against pruning and fine-tuning attacks. Compared to existing methods, the proposed method significantly improves effectiveness at very low watermarking rates.
Remote sensing object detection (RSOD) models are widely deployed on edge devices for critical applications. Their security and integrity have become urgent concerns. This work proposes a fragile model watermarking method that enables black-box integrity verification for RSOD models. Specifically, for a given RSOD model, we construct class-specific sensitive object triggers and corresponding fragile watermark samples for each target category. During the trigger generation process, a trained surrogate model is first employed to construct the initial sensitive object trigger, where real objects are utilized to guide the trigger to acquire weak semantic features of the target class. This trigger is then jointly optimized using both the original model and a tampered version. The original model ensures that the trigger remains recognizable, while the tampered model encourages sensitivity to parameter changes. During integrity verification, the model is queried with all the fragile watermark samples. The model is considered intact only if all predictions match the expected results. Extensive experiments demonstrate that the proposed method is effective across multiple RSOD models. It exhibits high sensitivity to various model modifications, including backdoor injection, fine-tuning, pruning, random parameter perturbation, and model compression.
Remote sensing object detection (RSOD) models play an increasingly important role in modern remote sensing systems. However, during model delivery, sharing, and deployment, RSOD models face increasing risks of unauthorized redistribution, illegal replication, and intellectual property infringement. To mitigate these threats, this paper proposes a white-box watermarking framework for RSOD models that enables reliable copyright verification while preserving the performance of the primary detection task. Specifically, a gradient-based sensitivity analysis of the detection loss is first performed to adaptively identify model parameters that minimally affect detection performance, which are then selected as watermark carriers. Subsequently, a parameter-ranking-based watermark encoding scheme is developed, where watermark bits are embedded by enforcing relative ordering constraints between parameter pairs. To further improve robustness under practical deployment conditions, an attack-simulation-driven training strategy is introduced, in which common perturbations and watermark removal attacks are simulated during the embedding process. In addition, a stealthiness enhancement strategy based on statistical distribution constraints is designed to maintain consistency between the distribution of watermarked parameters and those of the original model, thereby reducing the risk of watermark exposure and localization. Extensive experiments across multiple RSOD datasets and detection architectures demonstrate that the proposed method achieves a high copyright verification success rate with negligible impact on detection accuracy and exhibits strong robustness and stealthiness against a variety of watermark removal attacks.