The large amount of data and dynamism in network structures make it very crucial to identify influential nodes in complex social networks. Both centrality measurebased and machine learning model-based methods tend to view node topology and node attribute separately, neglecting the important interaction between structural links and node-level information. Efficient identification of influential nodes demands an integrated strategy that embodies the two facets. In order to meet such a challenge, a new framework named Scalable Quantum Non-local Neural Network with Energy Valley Optimization (SQNLNNet-EVO) is presented. The steps start with the preprocessing of the data by Correlation Coefficients with Min-Max Normalization (CCMMN) that enhances the high-correlation features and preserves the lowcorrelation signals. The feature extraction task is carried out with Steerable Transformers (ST), consisting of steerable convolution layers and a hybrid positional encoding scheme that provides rotation-equivariant attention mapping, and robust dependency learning. Fundamentally, SQNLNNet encodes classical node information into quantum states using phase encoding and Hadamard gates and uses the quantum non-locality to encode complex node and network interactions. Lastly, Energy Valley Optimization (EVO) enhances convergence and improves detection accuracy. The conducted experiments indicate that the proposed SQNLNNet-EVO model provides $99.8 \%$ accuracy, precision, recall, AUC, and F1-score with mere 1.75 seconds of computation time. Moreover, it achieves a Top-50 Influential Node Match of 98.1 percent, which is far better than the current methods. These results make SQNLNNet-EVO a time-saving and effective method to identify influential nodes in dynamic social networks.
The large amount of data and dynamism in network structures make it very crucial to identify influential nodes in complex social networks. Both centrality measurebased and machine learning model-based methods tend to view node topology and node attribute separately, neglecting the important interaction between structural links and node-level information. Efficient identification of influential nodes demands an integrated strategy that embodies the two facets. In order to meet such a challenge, a new framework named Scalable Quantum Non-local Neural Network with Energy Valley Optimization (SQNLNNet-EVO) is presented. The steps start with the preprocessing of the data by Correlation Coefficients with Min-Max Normalization (CCMMN) that enhances the high-correlation features and preserves the lowcorrelation signals. The feature extraction task is carried out with Steerable Transformers (ST), consisting of steerable convolution layers and a hybrid positional encoding scheme that provides rotation-equivariant attention mapping, and robust dependency learning. Fundamentally, SQNLNNet encodes classical node information into quantum states using phase encoding and Hadamard gates and uses the quantum non-locality to encode complex node and network interactions. Lastly, Energy Valley Optimization (EVO) enhances convergence and improves detection accuracy. The conducted experiments indicate that the proposed SQNLNNet-EVO model provides 99.8% accuracy, precision, recall, AUC, and F1-score with mere 1.75 seconds of computation time. Moreover, it achieves a Top-50 Influential Node Match of 98.1 percent, which is far better than the current methods. These results make SQNLNNet-EVO a time-saving and effective method to identify influential nodes in dynamic social networks.
Identifying influential nodes in complex networks is essential for a wide range of applications, from social network analysis to enhancing infrastructure resilience. While quantum walk-based methods offer potential advantages, existing approaches face challenges in dimensionality, computational efficiency, and accuracy. To address these limitations, this study proposes a novel method inspired by the one-dimensional discrete-time quantum walk (IOQW). This design enables the development of a simplified shift operator that leverages both self-loops and the network's structural connectivity. Furthermore, degree centrality and path-based features are integrated into the coin operator, enhancing the accuracy and scalability of the IOQW framework. Comparative evaluations against state-of-the-art quantum and classical methods demonstrate that IOQW excels in capturing both local and global topological properties while maintaining a low computational complexity of O(N⟨k⟩), where ⟨k⟩ denotes the average degree. These advancements establish IOQW as a powerful and practical tool for influential node identification in complex networks, bridging quantum-inspired techniques with real-world network science applications.
In this research, the computational efficiency of large-scale social network analysis is enhanced by the use of quantum random walk algorithms. The goal of this project is to address the need for high-efficiency centralized analysis of large-scale, heterogeneous social networks, community discovery, and dynamic effect mapping. In a theoretically sound framework of quantum random walks, amplitude superposition and unitary evolution principles have been used to improve both the sensitivity to local and global aspects. The solution uses real social network data with up to 5,000 nodes and more than 60,000 edges, and the testing results demonstrate its excellent scalability and fast convergence. Quantum algorithms have discovered community divisions and cut the mixing time by roughly 2.3 times after multiple optimizations. The performance indicators demonstrate that the above method has greatly improved key node detection accuracy and computation time as compared to the conventional baseline model in noisy situations. According to the aforementioned research, quantum-inspired algorithms have been used to expedite the analysis of large-scale data and reveal hidden structures that are challenging to identify using conventional techniques, such as bridge nodes and core-periphery distributions. The research assist data-driven choices in digital social ecosystems and lay the groundwork for in-depth network analysis.
Identifying key nodes in networks is a fundamental problem in network science. This study proposes a quantum deep reinforcement learning (QDRL) framework that integrates reinforcement learning with a variational quantum graph neural network, effectively identifying distributed influential nodes while preserving the network's fundamental topological properties. By leveraging principles of quantum computing, our method is designed to reduce model parameters and computational complexity compared to traditional neural networks. Trained on small networks, it demonstrated strong generalization across diverse scenarios. We compared the proposed algorithm with some classical node ranking and network dismantling algorithms on various synthetical and empirical networks. The results suggest that the proposed algorithm outperforms existing baseline methods. Moreover, in synthetic networks based on Erdős-Rényi and Watts-Strogatz models, QDRL demonstrated its capability to alleviate the issue of localization in network information propagation and node influence ranking. Our research provides insights into addressing fundamental problems in complex networks using quantum machine learning, demonstrating the potential of quantum approaches for network analysis tasks.
There is a pressing need for anomaly detection algorithms that can handle large amounts of diverse traffic data due to the quick growth of networked systems and the sophistication of contemporary cyberattacks. Despite the widespread use of conventional machine learning techniques for network intrusion detection, feature representation constraints, dataset imbalance, and the computational expense of scaling to vast problem spaces sometimes restrict their efficacy. In the meantime, new developments in quantum-assisted computation have opened up exciting possibilities for using quantum state changes to improve the feature learning process. Using the NF-UNSWNB15-v2 benchmark, this research presents HybridQCNN, a unique quantum-classical computing framework for binary classification of network traffic.The proposed architecture combines standard preprocessing techniques with an 8-qubit Parameterized Quantum Circuit (PQC) featuring multiple variational layers, where IsingXX and IsingYY entangling operations are applied to encode interfeature correlations, and a subsequent fully connected classical layer handles the final binary decision. A rigorous leakage-free data partitioning protocol was enforced, ensuring that all preprocessing transformations—including feature encoding, normalization, and threshold computation—were derived exclusively from the training subset, thereby preventing any information leakage from held-out partitions during evaluation. Experimental validation on a class-balanced subset of 60,000 traffic records yielded a classification accuracy of 97.33%, an F1-score of 0.9730, and a malicious traffic detection precision of 98.38%. Furthermore, the model achieved an AUC-ROC of 0.9861, reflecting strong class-level discriminability. Despite this performance, the entire model contains only 489 trainable parameters, underscoring the parameter efficiency of hybrid architectures relative to conventional deep learning baselines. These results suggest that integrating variational quantum circuits with classical inference modules provides an effective and scalable solution for network anomaly detection.
Weaknesses arising from heterogeneous device structure, high-dimensional traffic patterns, and more complex nonlinear attack behaviors. The traditional intrusion detection systems (IDS), which rely on the classical machine learning models, often face the challenges of scalability, feature explosion, and low representational ability when handling large-scale IoT traffic data. To meet these challenges, we propose a Hybrid Quantum-Classical Variational Neural Network (HQCVNN) for effective intrusion detection in IoT systems. The model utilizes a Variational Quantum Circuit (VQC) as a nonlinear quantum feature map followed by dense neural layers for overall classification. Angle embedding with entanglement layers enables the encoding of quantum data and leads to a better separability of features in high-dimensional space, whilst the classical optimization guarantees efficient training on NISQ time scales. The model is implemented using Qiskit and evaluated on classical benchmark intrusion detection datasets. Experimental results show the proposed method has better classification accuracy, F1-score, and complexity reduction than conventional ANNs and SVMs. The results demonstrate the promise of hybrid quantum machine learning systems with end-to-end general-purpose capabilities in future IoT security and provide pragmatic impressions on how to deploy them on near-term quantum processors.
The rise of deepfake technologies has posed significant challenges to privacy, security, and information integrity, particularly in audio and multimedia content. This paper introduces a Quantum-Trained Convolutional Neural Network (QT-CNN) framework designed to enhance the detection of deepfake audio, leveraging the computational power of quantum machine learning (QML). The QT-CNN employs a hybrid quantum-classical approach, integrating Quantum Neural Networks (QNNs) with classical neural architectures to optimize training efficiency while reducing the number of trainable parameters. Our method incorporates a novel quantum-to-classical parameter mapping that effectively utilizes quantum states to enhance the expressive power of the model, achieving up to 70% parameter reduction compared to classical models without compromising accuracy. Data pre-processing involved extracting essential audio features, label encoding, feature scaling, and constructing sequential datasets for robust model evaluation. Experimental results demonstrate that the QT-CNN achieves comparable performance to traditional CNNs, maintaining high accuracy during training and testing phases across varying configurations of QNN blocks. The QT framework’s ability to reduce computational overhead while maintaining performance underscores its potential for real-world applications in deepfake detection and other resource-constrained scenarios. This work highlights the practical benefits of integrating quantum computing into artificial intelligence, offering a scalable and efficient approach to advancing deepfake detection technologies.