A deep learning (DL)-enabled semantic communication (SemCom) has emerged as a 6G enabler while promising to minimize power usage, bandwidth consumption, and transmission delay by minimizing irrelevant information transmission. However, the benefits of such a semantic-centric design can be limited by radio frequency interference (RFI) that causes substantial semantic noise. The impact of semantic noise due to interference can be alleviated using an interference-resistant and robust (IR$^2$) SemCom design. Nevertheless, no such design exists yet. To shed light on this knowledge gap and stimulate fundamental research on IR$^2$ SemCom, the performance limits of a text SemCom system named DeepSC are studied in the presence of (multi-interferer) RFI. By introducing a principled probabilistic framework for SemCom, we show that DeepSC produces semantically irrelevant sentences as the power of (multi-interferer) RFI gets very large. We also derive DeepSC's practical limits and a lower bound on its outage probability under multi-interferer RFI. Toward a fundamental 6G design for an IR$^2$ SemCom, moreover, we propose a generic lifelong DL-based IR$^2$ SemCom system. Eventually, we corroborate the derived performance limits with Monte Carlo simulations and computer experiments, which also affirm the vulnerability of DeepSC and DL-enabled text SemCom to a wireless attack using RFI.

翻译：深度学习赋能的语义通信（SemCom）作为6G使能技术有望通过最小化无关信息传输来降低功耗、带宽消耗和传输延迟。然而，这种语义中心设计的优势可能受到射频干扰（RFI）的限制，该干扰会引发严重的语义噪声。采用抗干扰鲁棒（IR$^2$）SemCom设计可缓解干扰导致的语义噪声影响，但目前尚不存在此类设计。为填补这一知识空白并推动IR$^2$ SemCom的基础研究，本文研究了存在（多干扰源）RFI环境下名为DeepSC的文本语义通信系统的性能极限。通过引入原则性的SemCom概率框架，我们发现当（多干扰源）RFI功率极大时，DeepSC会产生语义无关的句子。我们还推导了DeepSC的实际性能极限以及多干扰源RFI条件下其中断概率的下界。此外，针对IR$^2$ SemCom的基础6G设计，我们提出了一种通用的终身深度学习驱动的IR$^2$ SemCom系统。最终，我们通过蒙特卡洛仿真和计算机实验验证了所推导的性能极限，同时证实了DeepSC及深度学习赋能的文本语义通信对无线RFI攻击的脆弱性。