Pathway to Secure and Trustworthy 6G for LLMs: Attacks, Defense, and Opportunities

Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that 6G mobile edge computing networks will be able to support LLMs as a service, as they provide ultra reliable low-latency communications and closed loop massive connectivity. However, LLMs are vulnerable to data and model privacy issues that affect the trustworthiness of LLMs to be deployed for user-based services. In this paper, we explore the security vulnerabilities associated with fine-tuning LLMs in 6G networks, in particular the membership inference attack. We define the characteristics of an attack network that can perform a membership inference attack if the attacker has access to the fine-tuned model for the downstream task. We show that the membership inference attacks are effective for any downstream task, which can lead to a personal data breach when using LLM as a service. The experimental results show that the attack success rate of maximum 92% can be achieved on named entity recognition task. Based on the experimental analysis, we discuss possible defense mechanisms and present possible research directions to make the LLMs more trustworthy in the context of 6G networks.

SelfFed: Self-supervised Federated Learning for Data Heterogeneity and Label Scarcity in IoMT

Self-supervised learning in federated learning paradigm has been gaining a lot of interest both in industry and research due to the collaborative learning capability on unlabeled yet isolated data. However, self-supervised based federated learning strategies suffer from performance degradation due to label scarcity and diverse data distributions, i.e., data heterogeneity. In this paper, we propose the SelfFed framework for Internet of Medical Things (IoMT). Our proposed SelfFed framework works in two phases. The first phase is the pre-training paradigm that performs augmentive modeling using Swin Transformer based encoder in a decentralized manner. The first phase of SelfFed framework helps to overcome the data heterogeneity issue. The second phase is the fine-tuning paradigm that introduces contrastive network and a novel aggregation strategy that is trained on limited labeled data for a target task in a decentralized manner. This fine-tuning stage overcomes the label scarcity problem. We perform our experimental analysis on publicly available medical imaging datasets and show that our proposed SelfFed framework performs better when compared to existing baselines concerning non-independent and identically distributed (IID) data and label scarcity. Our method achieves a maximum improvement of 8.8% and 4.1% on Retina and COVID-FL datasets on non-IID dataset. Further, our proposed method outperforms existing baselines even when trained on a few (10%) labeled instances.

ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review

ChatGPT is another large language model (LLM) inline but due to its performance and ability to converse effectively, it has gained a huge popularity amongst research as well as industrial community. Recently, many studies have been published to show the effectiveness, efficiency, integration, and sentiments of chatGPT and other LLMs. In contrast, this study focuses on the important aspects that are mostly overlooked, i.e. sustainability, privacy, digital divide, and ethics and suggests that not only chatGPT but every subsequent entry in the category of conversational bots should undergo Sustainability, PrivAcy, Digital divide, and Ethics (SPADE) evaluation. This paper discusses in detail about the issues and concerns raised over chatGPT in line with aforementioned characteristics. We support our hypothesis by some preliminary data collection and visualizations along with hypothesized facts. We also suggest mitigations and recommendations for each of the concerns. Furthermore, we also suggest some policies and recommendations for AI policy act, if designed by the governments.

SPIN: Simulated Poisoning and Inversion Network for Federated Learning-Based 6G Vehicular Networks

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.

AI and 6G into the Metaverse: Fundamentals, Challenges and Future Research Trends

Since Facebook was renamed Meta, a lot of attention, debate, and exploration have intensified about what the Metaverse is, how it works, and the possible ways to exploit it. It is anticipated that Metaverse will be a continuum of rapidly emerging technologies, usecases, capabilities, and experiences that will make it up for the next evolution of the Internet. Several researchers have already surveyed the literature on artificial intelligence (AI) and wireless communications in realizing the Metaverse. However, due to the rapid emergence of technologies, there is a need for a comprehensive and in-depth review of the role of AI, 6G, and the nexus of both in realizing the immersive experiences of Metaverse. Therefore, in this survey, we first introduce the background and ongoing progress in augmented reality (AR), virtual reality (VR), mixed reality (MR) and spatial computing, followed by the technical aspects of AI and 6G. Then, we survey the role of AI in the Metaverse by reviewing the state-of-the-art in deep learning, computer vision, and edge AI. Next, we investigate the promising services of B5G/6G towards Metaverse, followed by identifying the role of AI in 6G networks and 6G networks for AI in support of Metaverse applications. Finally, we enlist the existing and potential applications, usecases, and projects to highlight the importance of progress in the Metaverse. Moreover, in order to provide potential research directions to researchers, we enlist the challenges, research gaps, and lessons learned identified from the literature review of the aforementioned technologies.

Industry 5.0 is Coming: A Survey on Intelligent NextG Wireless Networks as Technological Enablers

Industry 5.0 vision, a step toward the next industrial revolution and enhancement to Industry 4.0, envisioned the new goals of resilient, sustainable, and human-centric approaches in diverse emerging applications, e.g., factories-of-the-future, digital society. The vision seeks to leverage human intelligence and creativity in nexus with intelligent, efficient, and reliable cognitive collaborating robots (cobots) to achieve zero waste, zerodefect, and mass customization-based manufacturing solutions. However, the vision requires the merging of cyber-physical worlds through utilizing Industry 5.0 technological enablers, e.g., cognitive cobots, person-centric artificial intelligence (AI), cyberphysical systems, digital twins, hyperconverged data storage and computing, communication infrastructure, and others. In this regard, the convergence of the emerging computational intelligence (CI) paradigm and next-generation wireless networks (NGWNs) can fulfill the stringent communication and computation requirements of the technological enablers in the Industry 5.0 vision, which is the aim of this survey-based tutorial. In this article, we address this issue by reviewing and analyzing current emerging concepts and technologies, e.g., CI tools and frameworks, network-in-box architecture, open radio access networks, softwarized service architectures, potential enabling services, and others, essential for designing the objectives of CINGWNs to fulfill the Industry 5.0 vision requirements. Finally, we provide a list of lessons learned from our detailed review, research challenges, and open issues that should be addressed in CI-NGWNs to realize Industry 5.0.

IIFNet: A Fusion based Intelligent Service for Noisy Preamble Detection in 6G

In this article, we present our vision of preamble detection in a physical random access channel for next-generation (Next-G) networks using machine learning techniques. Preamble detection is performed to maintain communication and synchronization between devices of the Internet of Everything (IoE) and next-generation nodes. Considering the scalability and traffic density, Next-G networks have to deal with preambles corrupted by noise due to channel characteristics or environmental constraints. We show that when injecting 15% random noise, the detection performance degrades to 48%. We propose an informative instance-based fusion network (IIFNet) to cope with random noise and to improve detection performance, simultaneously. A novel sampling strategy for selecting informative instances from feature spaces has also been explored to improve detection performance. The proposed IIFNet is tested on a real dataset for preamble detection that was collected with the help of a reputable commercial company.

Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT data

The past decade has seen a rapid adoption of Artificial Intelligence (AI), specifically the deep learning networks, in Internet of Medical Things (IoMT) ecosystem. However, it has been shown recently that the deep learning networks can be exploited by adversarial attacks that not only make IoMT vulnerable to the data theft but also to the manipulation of medical diagnosis. The existing studies consider adding noise to the raw IoMT data or model parameters which not only reduces the overall performance concerning medical inferences but also is ineffective to the likes of deep leakage from gradients method. In this work, we propose proximal gradient split learning (PSGL) method for defense against the model inversion attacks. The proposed method intentionally attacks the IoMT data when undergoing the deep neural network training process at client side. We propose the use of proximal gradient method to recover gradient maps and a decision-level fusion strategy to improve the recognition performance. Extensive analysis show that the PGSL not only provides effective defense mechanism against the model inversion attacks but also helps in improving the recognition performance on publicly available datasets. We report 17.9$\%$ and 36.9$\%$ gains in accuracy over reconstructed and adversarial attacked images, respectively.

Towards Energy Efficient Distributed Federated Learning for 6G Networks

The provision of communication services via portable and mobile devices, such as aerial base stations, is a crucial concept to be realized in 5G/6G networks. Conventionally, IoT/edge devices need to transmit the data directly to the base station for training the model using machine learning techniques. The data transmission introduces privacy issues that might lead to security concerns and monetary losses. Recently, Federated learning was proposed to partially solve privacy issues via model-sharing with base station. However, the centralized nature of federated learning only allow the devices within the vicinity of base stations to share the trained models. Furthermore, the long-range communication compels the devices to increase transmission power, which raises the energy efficiency concerns. In this work, we propose distributed federated learning (DBFL) framework that overcomes the connectivity and energy efficiency issues for distant devices. The DBFL framework is compatible with mobile edge computing architecture that connects the devices in a distributed manner using clustering protocols. Experimental results show that the framework increases the classification performance by 7.4\% in comparison to conventional federated learning while reducing the energy consumption.

Multimodal-Boost: Multimodal Medical Image Super-Resolution using Multi-Attention Network with Wavelet Transform

Multimodal medical images are widely used by clinicians and physicians to analyze and retrieve complementary information from high-resolution images in a non-invasive manner. The loss of corresponding image resolution degrades the overall performance of medical image diagnosis. Deep learning based single image super resolution (SISR) algorithms has revolutionized the overall diagnosis framework by continually improving the architectural components and training strategies associated with convolutional neural networks (CNN) on low-resolution images. However, existing work lacks in two ways: i) the SR output produced exhibits poor texture details, and often produce blurred edges, ii) most of the models have been developed for a single modality, hence, require modification to adapt to a new one. This work addresses (i) by proposing generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data. Existing approaches based on the GAN have yielded good SR results; however, the texture details of their SR output have been experimentally confirmed to be deficient for medical images particularly. The integration of wavelet transform (WT) and GANs in our proposed SR model addresses the aforementioned limitation concerning textons. The WT divides the LR image into multiple frequency bands, while the transferred GAN utilizes multiple attention and upsample blocks to predict high-frequency components. Moreover, we present a learning technique for training a domain-specific classifier as a perceptual loss function. Combining multi-attention GAN loss with a perceptual loss function results in a reliable and efficient performance. Applying the same model for medical images from diverse modalities is challenging, our work addresses (ii) by training and performing on several modalities via transfer learning.