With the advancement of deep learning, DNNs have been widely deployed across diverse domains. Model-as-a-Service (MaaS) platforms allow enterprises to commercialize well-trained models, which are built through extensive data collection and substantial computational investment. Consequently, protecting these models from unauthorized use and intellectual property (IP) theft has become critical. While watermarking has emerged as a prominent IP protection technique, most existing approaches target centralized settings, leaving federated learning (FL) scenarios largely underexplored. To bridge this gap, we propose Federated Watermarking with Distributed Verification (FWDV), a novel framework tailored for FL. FWDV enables each client to independently verify watermark ownership and jointly defend the model against erasure attempts. To our knowledge, this is the first work to achieve both distributed verification and robustness against a broad spectrum of attacks. Extensive experiments demonstrate that FWDV embeds watermarks with minimal impact on model utility and resists removal through fine-tuning, pruning, and distillation.

In recent years, the notion of federated learning (FL) has led to the new paradigm of distributed artificial intelligence (AI) with privacy preservation. However, most current FL systems suffer from data privacy issues due to the requirement of a trusted third party. Although some previous works introduce differential privacy to protect the data, however, it may also significantly deteriorate the model performance. To address these issues, we propose a novel decentralized collaborative AI framework, named Auditable Homomorphic-based Decentralised Collaborative AI (AerisAI), to improve security with homomorphic encryption and fine-grained differential privacy. Our proposed AerisAI directly aggregates the encrypted parameters with a blockchain-based smart contract to get rid of the need of a trusted third party. We also propose a brand-new concept for eliminating the negative impacts of differential privacy for model performance. Moreover, the proposed AerisAI also provides the broadcast-aware group key management based on ciphertext-policy attribute-based encryption (CP-ABE) to achieve fine-grained access control based on different service-level agreements. We provide a formal theoretical analysis of the proposed AerisAI as well as the functionality comparison with the other baselines. We also conduct extensive experiments on real datasets to evaluate the proposed approach. The experimental results indicate that our proposed AerisAI significantly outperforms the other state-of-the-art baselines.

For machine learning in online social networks or mobile environments, data privacy-preserving is a very important issue. In the past, artificial intelligence and machine learning algorithms that operating on a stand-alone machine must analyze each data in order to build an accurate model when training a model. However, this method is insufficient in terms of privacy protection, because it must collect data from different sources; on the other hand, if these algorithms analyze only a part of the data, the accuracy of the models constructed by artificial intelligence and machine learning algorithms will be very low. To solve the above problems, this study starts from the privacy protection aspect of industrial data management, combined with the concept of federated learning, and hopes to improve the accuracy of algorithm modules while ensuring data privacy. Therefore, in this paper, we analyze the impact of federated learning under different protocol mechanisms on the accuracy of algorithm modules, and based on this, we can apply this module to integrate blockchain smart contract technology in the future.

In this paper, we propose a novel system to estimate depth maps of outdoor scenes from a video sequence. According to the characteristics of a video, our approach considers more information in the temporal domain than the traditional depth reconstruction methods. We perform Structure From Motion (SfM) on consecutive image frames from a video from SIFT feature point correspondences, which provides some camera information, including 3D translation and rotation, for all the images. Then, we compute the constrained optical flow between selected scenes so that we can solve an over-constrained linear system to estimate the depth map for all pixels at each frame. In addition, mean shift image segmentation is incorporated to aggregate the depth estimation. Thus, this initial depth map is used as the data term of our pixel-based and region-based Markov Random Field (MRF) formulation for depth map estimation. The proposed MRF depth estimation not only imposes adaptive smoothness constraints but also includes sky detection in the final depth map estimation. By minimizing the associated MRF energy function for each frame, we obtain refined depth maps that achieve detail-preserving and temporally consistent depth estimation results.