Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be exposed through gradient inversion attacks. While earlier analytical methods have demonstrated success in reconstructing input data from fully connected layers, their effectiveness significantly diminishes when applied to convolutional layers, high-dimensional inputs, and scenarios involving multiple training examples. This paper extends our previous work as reported (Eltaras in International Conference on Web Information Systems Engineering, Springer, Singapore, 2024) and proposes three advanced algorithms to broaden the applicability of gradient inversion attacks. The first algorithm presents a novel data leakage method that efficiently exploits convolutional layer gradients, demonstrating that even with non-fully invertible activation functions, such as ReLU, training samples can be analytically reconstructed directly from gradients without the need to reconstruct intermediate layer outputs. Building on this foundation, the second algorithm extends this analytical approach to support high-dimensional input data, substantially enhancing its utility across complex real-world datasets. The third algorithm introduces an innovative analytical method for reconstructing mini-batches, addressing a critical gap in current research that predominantly focuses on reconstructing only a single training example. Unlike previous studies that focused mainly on the weight constraints of convolutional layers, our approach emphasizes the pivotal role of gradient constraints, revealing that successful attacks can be executed with fewer than 5% of the constraints previously deemed necessary in certain layers.

Quantum computing has emerged as a promising field with the potential to revolutionize information processing and storage. Understanding its current state and research trajectory is crucial. This study aims to map the current literature on quantum computing, to identify how quantum computing is being used in solving quantum software problems and improving quantum algorithms. Moreover, it examines evaluation parameters and the challenges faced in this field. A systematic mapping study was conducted using the SCOPUS database, including all papers up to December 2024. Relevant articles were selected based on inclusion criteria, and a content analysis was performed to categorize and synthesize the findings. Information was gathered from 33 primary studies. Findings show that quantum computing is mainly applied in machine learning and optimization, though classical methods still outperform it. IBM Quantum is the most used platform. Research focuses on algorithm efficiency, verification over validation, and resource optimization, but lacks standardized evaluation methods. Key limitations include hardware constraints, noise, and scalability, while challenges involve integration, error correction, and problem formulation. Quantum computing continues to face significant technological challenges, but current research lays the groundwork for future advances. More practical studies on real hardware and strategies to improve the implementation and performance of quantum algorithms are needed. Effective evaluation, verification, and validation of quantum solutions must be further investigated.