Neural Style Transfer (NST) is a popular technique of computer vision where the content of an image is blended with the style of another, which results in a fused image with certain properties of both original images. This approach has practical applications in various domains and has garnered significant attention in both industry and academia. An interesting application of this technique is segmented style transfer where a segmentation algorithm is used to locate objects within an image and then the style transfer method is performed locally, producing images with different styles for different objects. This approach opens up possibilities for creating visually striking compositions by seamlessly blending various artistic styles onto specific objects within an image, allowing for a new level of creative expression. This paper proposes a novel method that combines Segment Anything Model (SAM), a state-of-the-art vision transformer-based image segmentation model developed by Facebook, with style transfer. Our approach includes performing localized style transfer in selected segmentation regions of an image using classical style transfer algorithms. To ensure smooth transitions between the stylized and non-stylized border we also develop our loss function with a border smoothing technique. Experimental results demonstrate the robustness and effectiveness of the proposed methodology, including the ability to infuse multiple artistic styles into different objects within an image. The contributions of this work include integrating SAM with style transfer, proposing a novel loss function, evaluating the segmented style transfer in multiple content regions, comparing with state-of-the-art approaches, and experimenting with multiple style images for diverse stylization. Our primary focus centers on creating a model that serves as a digital painter across a wide range of image genres and artistic styles.

Federated Learning is identified as a reliable technique for distributed training of ML models. Specifically, a set of dispersed nodes may collaborate through a federation in producing a jointly trained ML model without disclosing their data to each other. Each node performs local model training and then shares its trained model weights with a server node, usually called Aggregator in federated learning, as it aggregates the trained weights and then sends them back to its clients for another round of local training. Despite the data protection and security that FL provides to each client, there are still well-studied attacks such as membership inference attacks that can detect potential vulnerabilities of the FL system and thus expose sensitive data. In this paper, in order to prevent this kind of attack and address private data leakage, we introduce FREDY, a differential private federated learning framework that enables knowledge transfer from private data. Particularly, our approach has a teachers–student scheme. Each teacher model is trained on sensitive, disjoint data in a federated manner, and the student model is trained on the most voted predictions of the teachers on public unlabeled data which are noisy aggregated in order to guarantee the privacy of each teacher’s sensitive data. Only the student model is publicly accessible as the teacher models contain sensitive information. We show that our proposed approach guarantees the privacy of sensitive data against model inference attacks while it combines the federated learning settings for the model training procedures.

Machine learning (ML) plays a growing role in the Internet of Things (IoT) applications and has efficiently contributed to many aspects, both for businesses and consumers, including proactive intervention, tailored experiences, and intelligent automation. Traditional cloud computing machine learning applications need the data, generated by IoT devices, to be uploaded and processed on a central server giving data access to third parties raising privacy and data ownership concerns. Federated learning (FL) is able to overcome these privacy concerns by enabling an on-device collaborative training of a machine learning model without sharing any data over the network. However, model sharing can also potentially reveal sensitive information. Therefore, federated learning needs additional privacy-preserving techniques to enable fully private machine learning model sharing and training. In this chapter, privacy-preserving techniques for federated learning arc studied. In addition, a comparative analysis of state-of-the-art federated learning frameworks against privacy-preserving techniques is presented. The analysis comprises the identification of main advantages and disadvantages for eight 118FL frameworks as well as the investigation of the frameworks under criteria related to their FL features and privacy preservation options. <!----> <!----> <!----> <!---->