Author

Rahim Taheri

h-index 17 View on Semantic Scholar

We have 4 of 45 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Defense-in-Depth at the Perception-Reasoning Interface of LLM-Centric Agentic UAV Swarms

Large Language Models (LLMs) increasingly support Uncrewed Aerial Vehicle (UAV) swarm operations such as data collection scheduling, where the model reads structured sensor reports and decides which sensors to visit. An adversary who quietly manipulates those reports can redirect the swarm without modifying the model w...

MohammadHossein Homaei, Yousef Emami, Sajad Homayoun et al. · 0 citations

#federated learning Sep 2026

V5GIDS: An ETSI NFV MANO-Aligned Federated Intrusion Detection Framework for 5G Networks

Experimental results show that V5GIDS achieves strong detection performance in the evaluated settings while improving deployment relevance through orchestration alignment, reduced telemetry exchange, and resource-aware distributed operation.

Sofian Ben Khalifa, Rahim Taheri, Ivan Jordanov · Journal of Network and Syste... · 0 citations

Review Jul 2026

LLM-Centric Agentic AI for UAV Swarms: Architecture, Enabling Technologies, and Open Problems

This paper proposes LLM-Centric Agentic AI for UAV Swarms (LAUS) and reviews key enabling technologies such as onboard and edge computing, 5G/6G connectivity, multimodal intelligence, and cybersecurity mechanisms, and analyzes threats such as Priority Manipulation Attacks (PMA) that can distort decision-making and degr...

Yousef Emami, Rahim Taheri, MohammadHossein Homaei et al. · arXiv.org · 0 citations

Aug 2026

Fed-blam: federated BERT and LLaMA for IoT malware detection

Experimental results demonstrate that the federated LLM-based models consistently outperform a multilayer perceptron baseline, with the LLaMA model achieving up to 99.9% accuracy and F1-score while generalising effectively to previously unseen device types.

Chloe Nazaruk, Rahim Taheri, Gelayol Golcarenarenji et al. · Journal of Supercomputing · 0 citations