# Joint Hybrid Beamforming and Artificial Noise Design for Secure Multi-UAV ISAC Networks

arXiv: https://arxiv.org/abs/2509.23687 · HTML: https://mlsanity.com/paper/2509.23687/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 28 Sep 2025.

## Builds on (most cited first, 5 of 5)

- [Large Language Model Based Multi-Objective Optimization for Integrated Sensing and Communications in UAV Networks](https://mlsanity.com/paper/2410.05062/) (2024)
- [Joint Maneuver and Beamforming Design for UAV-Enabled Integrated Sensing and Communication](https://mlsanity.com/paper/2110.02857/) (2021)
- [ISAC from the Sky: UAV Trajectory Design for Joint Communication and Target Localization](https://mlsanity.com/paper/2207.02904/) (2022)
- [Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning](https://mlsanity.com/paper/2306.02990/) (2023)
- [UAV-Enabled Secure ISAC Against Dual Eavesdropping Threats: Joint Beamforming and Trajectory Design](https://mlsanity.com/paper/2412.19748/) (2024)

## Abstract (arXiv)

Integrated sensing and communication (ISAC) emerges as a key enabler for next-generation applications such as smart cities and autonomous systems. Its integration with unmanned aerial vehicles (UAVs) unlocks new potentials for reliable communication and precise sensing in dynamic aerial environments. However, existing research predominantly treats UAVs as aerial base stations, overlooking their role as ISAC users, and fails to leverage large-scale antenna arrays at terrestrial base stations to enhance security and spectral efficiency. This paper propose a secure and spectral efficient ISAC framework for multi-UAV networks, and a two-stage optimization approach is developed to jointly design hybrid beamforming (HBF), artificial noise (AN) injection, and UAV trajectories. Aiming at maximizing the sum secrecy rate, the first stage employs Proximal Policy Optimization (PPO) to optimize digital beamformers and trajectories, and the second stage decomposes the digital solution into analog and digital components via low-complexity matrix factorization. Simulation results demonstrate the effectiveness of the proposed framework compared to benchmark schemes.