arXiv subjects

Habeeb Olufowobi

Publications and source records attributed to Habeeb Olufowobi.

6 recordsLinked to original sources

arXiv2026

Toward Inherently Robust VLMs Against Visual Perception Attacks

Autonomous vehicles rely on deep neural networks (DNNs) for traffic sign recognition, lane centering, and vehicle detection, yet these models are vulnerable to attacks that induce misclassification and threaten safety. Existing defenses (e.g., adversarial training) often fail to generalize and degrade clean accuracy. We introduce Vehicle Vision-Language Models (V2LMs), fine-tuned vision-language models specialized for autonomous vehicle perception, and show that they are inherently more robust to unseen attacks without adversarial training, maintaining substantially higher adversarial accuracy than conventional DNNs. We study two deployments: Solo (task-specific V2LMs) and Tandem (a single V2LM for all three tasks). Under attacks, DNNs drop 33-74%, whereas V2LMs decline by under 8% on average. Tandem achieves comparable robustness to Solo while being more memory-efficient. We also explore integrating V2LMs in parallel with existing perception stacks to enhance resilience. Our results suggest V2LMs are a promising path toward secure, robust AV perception.

cs.CV↗

arXiv2026

MorphXAI: An Explainable Framework for Morphological Analysis of Parasites in Blood Smear Images

Parasitic infections remain a pressing global health challenge, particularly in low-resource settings where diagnosis still depends on labor-intensive manual inspection of blood smears and the availability of expert domain knowledge. While deep learning models have shown strong performance in automating parasite detection, their clinical usefulness is constrained by limited interpretability. Existing explainability methods are largely restricted to visual heatmaps or attention maps, which highlight regions of interest but fail to capture the morphological traits that clinicians rely on for diagnosis. In this work, we present MorphXAI, an explainable framework that unifies parasite detection with fine-grained morphological analysis. MorphXAI integrates morphological supervision directly into the prediction pipeline, enabling the model to localize parasites while simultaneously characterizing clinically relevant attributes such as shape, curvature, visible dot count, flagellum presence, and developmental stage. To support this task, we curate a clinician-annotated dataset of three parasite species (Leishmania, Trypanosoma brucei, and Trypanosoma cruzi) with detailed morphological labels, establishing a new benchmark for interpretable parasite analysis. Experimental results show that MorphXAI not only improves detection performance over the baseline but also provides structured, biologically meaningful explanations.

cs.CV↗

arXiv2025

CTMap: LLM-Enabled Connectivity-Aware Path Planning in Millimeter-Wave Digital Twin Networks

In this paper, we present \textit{CTMAP}, a large language model (LLM) empowered digital twin framework for connectivity-aware route navigation in millimeter-wave (mmWave) wireless networks. Conventional navigation tools optimize only distance, time, or cost, overlooking network connectivity degradation caused by signal blockage in dense urban environments. The proposed framework constructs a digital twin of the physical mmWave network using OpenStreetMap, Blender, and NVIDIA Sionna's ray-tracing engine to simulate realistic received signal strength (RSS) maps. A modified Dijkstra algorithm then generates optimal routes that maximize cumulative RSS, forming the training data for instruction-tuned GPT-4-based reasoning. This integration enables semantic route queries such as ``find the strongest-signal path'' and returns connectivity-optimized paths that are interpretable by users and adaptable to real-time environmental updates. Experimental results demonstrate that CTMAP achieves up to a tenfold improvement in cumulative signal strength compared to shortest-distance baselines, while maintaining high path validity. The synergy of digital twin simulation and LLM reasoning establishes a scalable foundation for intelligent, interpretable, and connectivity-driven navigation, advancing the design of AI-empowered 6G mobility systems.

cs.NI↗

arXiv2025

FedVLM: Scalable Personalized Vision-Language Models through Federated Learning

Vision-language models (VLMs) demonstrate impressive zero-shot and few-shot learning capabilities, making them essential for several downstream tasks. However, fine-tuning these models at scale remains challenging, particularly in federated environments where data is decentralized and non-iid across clients. Existing parameter-efficient tuning methods like LoRA (Low-Rank Adaptation) reduce computational overhead but struggle with heterogeneous client data, leading to suboptimal generalization. To address these challenges, we propose FedVLM, a federated LoRA fine-tuning framework that enables decentralized adaptation of VLMs while preserving model privacy and reducing reliance on centralized training. To further tackle data heterogeneity, we introduce personalized LoRA (pLoRA), which dynamically adapts LoRA parameters to each client's unique data distribution, significantly improving local adaptation while maintaining global model aggregation. Experiments on the RLAIF-V dataset show that pLoRA improves client-specific performance by 24.5% over standard LoRA, demonstrating superior adaptation in non-iid settings. FedVLM provides a scalable and efficient solution for fine-tuning VLMs in federated settings, advancing personalized adaptation in distributed learning scenarios.

cs.CV↗

arXiv2025

Enhancing Graph Neural Networks: A Mutual Learning Approach

Knowledge distillation (KD) techniques have emerged as a powerful tool for transferring expertise from complex teacher models to lightweight student models, particularly beneficial for deploying high-performance models in resource-constrained devices. This approach has been successfully applied to graph neural networks (GNNs), harnessing their expressive capabilities to generate node embeddings that capture structural and feature-related information. In this study, we depart from the conventional KD approach by exploring the potential of collaborative learning among GNNs. In the absence of a pre-trained teacher model, we show that relatively simple and shallow GNN architectures can synergetically learn efficient models capable of performing better during inference, particularly in tackling multiple tasks. We propose a collaborative learning framework where ensembles of student GNNs mutually teach each other throughout the training process. We introduce an adaptive logit weighting unit to facilitate efficient knowledge exchange among models and an entropy enhancement technique to improve mutual learning. These components dynamically empower the models to adapt their learning strategies during training, optimizing their performance for downstream tasks. Extensive experiments conducted on three datasets each for node and graph classification demonstrate the effectiveness of our approach.

cs.LG↗

arXiv2025

Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of Autonomous Vehicles

We present a novel physical-world attack on autonomous vehicle (AV) lane detection systems that leverages negative shadows -- bright, lane-like patterns projected by passively redirecting sunlight through occluders. These patterns exploit intensity-based heuristics in modern lane detection (LD) algorithms, causing AVs to misclassify them as genuine lane markings. Unlike prior attacks, our method is entirely passive, power-free, and inconspicuous to human observers, enabling legal and stealthy deployment in public environments. Through simulation, physical testbed, and controlled field evaluations, we demonstrate that negative shadows can cause up to 100% off-road deviation or collision rates in specific scenarios; for example, a 20-meter shadow leads to complete off-road exits at speeds above 10 mph, while 30-meter shadows trigger consistent lane confusion and collisions. A user study confirms the attack's stealthiness, with 83.6% of participants failing to detect it during driving tasks. To mitigate this threat, we propose Luminosity Filter Pre-processing, a lightweight defense that reduces attack success by 87% through brightness normalization and selective filtering. Our findings expose a critical vulnerability in current LD systems and underscore the need for robust perception defenses against passive, real-world attacks.

cs.CR↗