Enhancing 6G Wireless Intelligence: Do LLMs Work for CSI Prediction?

In high-mobility 6G scenarios, rapidly time-varying channels lead to very short coherence times, which makes conventional pilot-based channel state information (CSI) estimation approaches prone to outdated information or excessive pilot overhead. Therefore, channel prediction becomes essential in such dynamic wireless systems. To address this challenge, large language models (LLMs) are emerging learning frameworks that have recently attracted attention for CSI prediction due to their strong sequence modeling capability and ability to generalize across different environments. This paper proposes an LLM-based framework for channel prediction in high-mobility orthogonal time frequency space (OTFS) communication systems. In this work, we develop a physics-aware LLM-based predictor that learns the temporal evolution of OTFS channel coefficients from historical channel observations while incorporating mobility-related physical descriptors (e.g., maximum Doppler frequency) to achieve accurate prediction of future channel states in rapidly time-varying environments. The effectiveness of the proposed framework is evaluated through extensive simulations under user velocities ranging from 100 to 500 km/h. Numerical results show that the proposed method consistently achieves lower normalized mean square error (NMSE) compared with both classical deep learning predictors and LLM-based predictors without physical channel descriptors. These results demonstrate the advantage of integrating mobility-related channel knowledge with LLM-based sequence modeling for channel prediction in highly dynamic OTFS systems.

Investigating the Jamming Attack on 5G NR Physical Channels

This study investigates the jamming attack on the orthogonal frequency-division multiplexing (OFDM) based physical channels in 5G new radio (NR) technology from the aspect of signal processing. Disrupting the orthogonality property between subcarriers (SCs) is considered as one of the jammers targets in OFDM based generations. Focusing on the orthogonality property, we propose a method to detect the attacked subcarriers, and then neutralize the jamming attack using a multiplicative signal. Thanks to studying the frequency aspect of the attacked signal, the proposed method is independent of the jammers transmitted power. Simulation results evaluate the detection performance of the proposed method with various numbers of OFDM subcarriers.

A lightweight Encryption Method For Privacy-Preserving in Process Mining

Novel technological achievements in the fields of business intelligence, business management and data science are based on real-time and complex virtual networks. Sharing data between a large number of organizations that leads to a system with high computational complexity is one of the considerable characteristics of the current business networks. Discovery, conformance and enhancement of the business processes are performed using the generated event logs. In this regard, one of the overlooked challenges is privacy-preserving in the field of process mining in the industry. To preserve the data-privacy with a low computational complexity structure that is a necessity for the current digital business technology, a novel lightweight encryption method based on Haar transform and a private key is proposed in this paper. We compare the proposed method with the well-known homomorphic cryptosystem and Walsh- Hadamard encryption (WHE) in terms of cryptography, computational complexity and structure vulnerability. The analyses show that the proposed method anonymizes the event logs with the lower complexity and more accuracy compared with two aforementioned cryptosystems, significantly.