With the continuous and fast-changing land-scape in communication networks and artificial intelligence (AI), the researchers are interested in expedited standardization and realization of 6G networks. Federated learning (FL) is one of the paradigms that allows the 6G networks to support a diverse range of devices. Very few studies address the problem of flexibility and heterogeneity for AI network architectures in FL paradigm, that could be a potential key changer for standardization and realization of 6G networks. However, they either consider width-only or depth-only to provide flexibility support. Furthermore, the existing studies do not address the problem of weight scale variation while performing the global model aggregation at the server side. In this regard, we propose flexible federated learning (FLEXFL) for the support of heterogeneous AI network architectures in 6G communication systems. The proposed network not only considers the width but also the depth of the network architecture to make it compliant with the global model aggregation. We also address weight scale variation (WSV) while updating the global model with weight normalization, which is one of the problems associated with existing studies. We perform experimental analysis on two publicly available datasets and a few network architectures to show the efficacy of the proposed approach. The results reveal that the FLEXFL outperforms existing state-of-the-art works in both the IID and non-IID settings, accordingly.

Post COVID-19 and recent advancement in terms of language models, researchers have shown a lot of interest in analyzing social media posts for analyzing mental state of the users. Social media platforms are the epitome of sharing individual thoughts and feelings through textual posts and linguistic cues. Therefore, the textual modality from social media posts can be leveraged for detecting early signs of stress, depression or other mental health conditions, accordingly. Existing methods mainly focus on the feature engineering, shallow learning, and employing of deep learning architectures to improve the mental state recognition performance. Seldom the study uses an established knowledge-base that is available to model mentalization and emotional aspect to improving the depression and stress recognition. In this regard, we propose emotion aware contrastive networks (EAC-net) that leverages the existing knowledge-base and propose some new ones to model the emotional and mentalization aspect in order to improve the recognition of stress and depression state from textual posts. Furthermore, we propose a feature-level fusion and weighting mechanism using gated recurrent units (GRUs) and self-attention layers to weight and select the important features. Last, the EAC-Net uses a supervised contrastive learning strategy to train the network. The proposed method is evaluated on four publicly available datasets. Experimental results reveal that the EAC-Net achieves state-of-the-art results by outperforming baselines and existing methods by atleast 1.86%, 0.72%, 3.43%, and 3.64% on four publicly available datasets using F1-measure as the evaluation metric.

In past, due to data and model security concerns, modern communication systems mainly focus on the use of edge computing devices for enabling immersive applications and services. Federated learning is one of the preferred solutions but it stresses the computation capability of the edge devices for immersive applications. Much research is now focusing on split learning as an alternative due to its ability of performing joint training with limited computing resources. However, split learning is also vulnerable to data reconstruction, feature space hijacking, and model inversion attacks, which are quite common concerning immersive applications such as Metaverse. In this regard, we propose a ZEro-Trust Attack (ZETA) framework for data reconstruction and model inversion attacks for autonomous vehicles opting for split learning strategies. We propose the joint training of client, server, and shadow models for both the reconstruction and main task to fool existing methods. Our experimental results demonstrate that the proposed method is capable of reconstructing client's data with an error of 0.0032. This study is proposed as a basis to design more sophisticated defense mechanisms for autonomous vehicles to protect user services in 5G/6G networks.

The fifth generation (5G) networks are designed to support a large range of diverse services with strict performance requirements. Studies suggest that, 5G uses machine learning technologies for variety of tasks ranging from network management, and resource optimization to automated services. The successful integration of 5G with machine learning has also led to the basis for 6G networks. However, the use of machine learning makes the 5G networks susceptible to adversarial attacks. A few works study the effect of differential privacy and adversarial attacks in the 5G systems let alone to provide the proposal of effective defense mechanism. This study proposes Denoising and Adversarial attack-based STacked AutoeNcoder (DASTAN) convolutional neural networks (CNN) to provide defense against a specific differential privacy attack, i.e. membership inference, optimized to detect the device or data distribution potentially used in the training process. DASTAN initiates an intentional attack to camouflage the characteristics of an authorized user from an adversary and uses a de noising stacked autoencoder to recover the information at service provider's end for RF fingerprinting. The aim of RF fingerprinting is to validate the authenticity and identity of the device to preserve the privacy of wireless network. Experimental results demonstrate the efficacy of DASTAN-CNN, which reduces the attack success rate by up to 52.69% in comparison to the case where no defense strategy is employed. The DASTAN-CNN also achieves 75.29% authorized user recognition rate for RF fingerprinting while reducing the attack success rate to 39.23%, which shows the effectiveness in terms of trade-off efficiency.

The applications concerning vehicular networks benefit from the vision of beyond 5G and 6G technologies such as ultra-dense network topologies, low latency, and high data rates. Vehicular networks have always faced data privacy preservation concerns, which lead to the advent of distributed learning techniques such as federated learning. Although federated learning has solved data privacy preservation issues to some extent, the technique is quite vulnerable to model inversion and model poisoning attacks. We assume that the design of defense mechanism and attacks are two sides of the same coin. Designing a method to reduce vulnerability requires the attack to be effective and challenging with real-world implications. In this work, we propose simulated poisoning and inversion network (SPIN) that leverages the optimization approach for reconstructing data from a differential model trained by a vehicular node and intercepted when transmitted to roadside unit (RSU). We then train a generative adversarial network (GAN) to improve the generation of data with each passing round and global update from the RSU, accordingly. Evaluation results show the qualitative and quantitative effectiveness of the proposed approach. The attack initiated by SPIN can reduce up to 22% accuracy on publicly available datasets while just using a single attacker. We assume that revealing the simulation of such attacks would help us find its defense mechanism in an effective manner.

The dynamic property and increasing complexity are the key challenges for modeling financial technology (FinTech)-related applications such as stock markets. Over the years, a lot of inflexible predictive strategies have been proposed for predicting stock price movements that failed to achieve satisfactory results especially when a market crash occurs. To cope with this challenge, we propose a prediction framework based on an adversarial training strategy using reinforcement learning for the said FinTech application. The framework uses a heterogeneous knowledge base, including stock prices, tweets, and global indicators. We propose a modified newton-divided difference polynomial (NDDP) for missing data imputation. The informative patterns representing the intrinsic characteristics of financial markets were extracted using long short-term memory networks (LSTM). The two adversarial networks are heterogeneous data fusion representing market crash (HDFM)$Q$-learning and confrontational$Q$-learning network. Both networks are trained in an adversarial fashion to increase the effectiveness of prediction even when the financial market is volatile. The experimental results show the importance of global indicators and the proposed adversarial learning network (ALN) for improving the predictive performance in comparison with the existing state-of-the-art works.

The use of aerial base stations, AI cloud, and satellite storage can help manage location, traffic, and specific application-based services for vehicular social networks. However, sharing of such data makes the vehicular network vulnerable to data and privacy leakage. In this regard, this article proposes an efficient and secure data sharing scheme using community segmentation and a blockchain-based framework for vehicular social networks. The proposed work considers similarity matrices that employ the dynamics of structural similarity, modularity matrix, and data compatibility. These similarity matrices are then passed through stacked autoencoders that are trained to extract encoded embedding. A density-based clustering approach is then employed to find the community segments from the information distances between the encoded embeddings. A blockchain network based on the Hyperledger Fabric platform is also adopted to ensure data sharing security. Extensive experiments have been carried out to evaluate the proposed data-sharing framework in terms of the sum of squared error, sharing degree, time cost, computational complexity, throughput, and CPU utilization for proving its efficacy and applicability. The results show that the CSB framework achieves a higher degree of SD, lower computational complexity, and higher throughput.

Stock movement prediction is regarded as one of the most difficult, meaningful, and attractive research issues in the field of financial markets. The stock price data have non-stationary, noisy, and non-linear characteristics which make the movement and its prediction a challenging task. In this paper, we propose a framework to predict the stock price movement using phase space reconstruction (PSR) and extreme learning machines (ELM). The uniqueness of the framework is reflected by its feature transformation technique which computes the information distance from the transformed features in phase space. The distance from phase space dimensions are modelled with ELM to predict the stock price movement. A decision-level fusion is performed on the ELM models trained using each category of features to improve the prediction performance. The framework has been validated on one of the challenging Borsa Istanbul (BIST 100) dataset which is a widely used dataset in stock price prediction studies. The results from the proposed framework are compared with the conventional machine learning pipeline as well as the baseline methods, i.e., random and Naïve approach to show the effectiveness in prediction performance. Experimental results reveal that the framework improves predictive performance by 4.5% in terms of F-measure values.