IEEE

A Reinforcement Learning-Based Retraining-Free Pruning for Encoder-Based Language Models

Abstract: Natural Language Processing (NLP) has achieved significant success in complex tasks across various domains, yet it also brings high computational costs and inference delays. Pruning, as a ...
IEEE

Swarm of MASSs Cyber-Security for Anti-Hijack System Based on Blockchain and Chaotic-Steganography Using VRF-PBFT and Encoder-Decoder Deep Neural Networks

Abstract: It is crucial to guarantee the remote operation safety of the Maritime Autonomous Surface Ships (MASS). In this paper, a cyber-security framework of the anti-hijack system in the swarm of ...