Will 6G Be Semantic Communications? Opportunities and Challenges From Task Oriented and Secure Communications to Integrated Sensing

This paper explores opportunities and challenges of task-oriented communications (TOC), also referred to as goal-oriented communications, and semantic communications (SemCom) for next-generation (NextG) communication networks through the integration of multi-task learning (MTL). This approach employs deep neural networks representing a dedicated encoder at the transmitter and multiple task-specific decoders at the receiver, collectively trained to handle diverse tasks including semantic information preservation, source input reconstruction, and integrated sensing and communications (ISAC). Performance is improved with this MTL approach compared to conventional communication and sensing schemes. To extend the applicability from point-to-point links to multi-receiver settings, we envision the deployment of decoders at various receivers, where decentralized learning addresses the challenges of communication load and privacy concerns, leveraging federated learning or split learning techniques that distribute model updates or split segments of models across decentralized nodes, respectively. However, the efficacy of this approach is contingent on the robustness of the employed deep learning models. We scrutinize potential vulnerabilities stemming from adversarial attacks during both training and testing phases. These attacks aim to manipulate both the inputs at the encoder at the transmitter and the signals received over the air on the receiver side, highlighting the importance of fortifying semantic information against potential multi-domain exploits. Overall, the joint and robust design of TOC, SemCom and ISAC in the MTL framework emerges as the key enabler for context-aware, resource-efficient, and secure communications ultimately needed in NextG network systems.