Usman Ghous

Anwar Shah, Rohan Farooq, Sajid Anwer et al.

The Internet of Vehicles (IoV) faces a dynamic, adversarial security environment where attackers adapt to defenses. Existing intrusion detection systems rely on static classifiers that fail to capture sequential decision-making, attacker adaptation, and uncertainty. We formulate IoV security as a sequential attacker-defender interaction and model defense as a reinforcement learning problem under partial observability. We propose Quantum Belief-Integrated Reinforcement Defense (Q-BIRD), using quantum-inspired belief representation to encode defender uncertainty about hidden attacker intent via amplitude-based states, enabling non-Bayesian belief evolution. Integrated into a Proximal Policy Optimization (PPO) defender, Q-BIRD selects cost-aware mitigation actions. In simulated environments with adaptive, probing attackers, Q-BIRD reduced cumulative mean damage, damage variance, and attack success rate (ASR) by 60.4%, 90.2%, and 50.0%, respectively, while increasing survival probability by 46.4%. Compared to classical Bayesian PPO, damage variance reduction and ASR improved by 10.2 times and 50%. Ablation and explainability analyses confirm that amplitude-based belief is the primary decision signal during strategy transitions when classical belief collapses, providing superior IoV security without additional hardware.

Saad Sohail, Muhammad Usama, Usman Ghous et al.

Hyperspectral imaging (HSI) provides rich spectral-spatial information across hundreds of contiguous bands, enabling precise material discrimination in applications such as environmental monitoring, agriculture, and urban analysis. However, the high dimensionality and spectral variability of HSI data pose significant challenges for feature extraction and classification. This paper presents EnergyFormer, a transformer-based framework designed to address these challenges through three key innovations: (1) Multi-Head Energy Attention (MHEA), which optimizes an energy function to selectively enhance critical spectral-spatial features, improving feature discrimination; (2) Fourier Position Embedding (FoPE), which adaptively encodes spectral and spatial dependencies to reinforce long-range interactions; and (3) Enhanced Convolutional Block Attention Module (ECBAM), which selectively amplifies informative wavelength bands and spatial structures, enhancing representation learning. Extensive experiments on the WHU-Hi-HanChuan, Salinas, and Pavia University datasets demonstrate that EnergyFormer achieves exceptional overall accuracies of 99.28\%, 98.63\%, and 98.72\%, respectively, outperforming state-of-the-art CNN, transformer, and Mamba-based models. The source code will be made available at https://github.com/mahmad000.