SpoofTrackBench: Interpretable AI for Spoof-Aware UAV Tracking and Benchmarking

2025-10-26

AI Summary

This paper addresses the challenges of evaluating robustness and ensuring reproducibility in Real-Time Localization and Tracking Systems (RTLS) under radar spoofing attacks. To this end, we propose the first modular and reproducible benchmarking framework. Methodologically, we design a decoupled dual-stream architecture—comprising a clean stream and a spoofing detection stream—to model three canonical radar spoofing types: drift, ghost, and mirror attacks. The framework integrates JPDA and GNN trackers, introduces a realistic offset metric to quantify assignment errors, and enables attack interpretability via trajectory offset visualization, clustering overlay, and spoofing injection timelines. Our contributions include an open-source benchmark framework, standardized evaluation protocols, and automated analytical tools—collectively enhancing transparency, comparability, and community verifiability in anti-spoofing tracking research.

Technology Category

• Computer Vision: Motion & Tracking
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Tracking, profiling, and countermeasures against them
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

SpoofTrackBench is a reproducible, modular benchmark for evaluating adversarial robustness in real-time localization and tracking (RTLS) systems under radar spoofing. Leveraging the Hampton University Skyler Radar Sensor dataset, we simulate drift, ghost, and mirror-type spoofing attacks and evaluate tracker performance using both Joint Probabilistic Data Association (JPDA) and Global Nearest Neighbor (GNN) architectures. Our framework separates clean and spoofed detection streams, visualizes spoof-induced trajectory divergence, and quantifies assignment errors via direct drift-from-truth metrics. Clustering overlays, injection-aware timelines, and scenario-adaptive visualizations enable interpretability across spoof types and configurations. Evaluation figures and logs are auto-exported for reproducible comparison. SpoofTrackBench sets a new standard for open, ethical benchmarking of spoof-aware tracking pipelines, enabling rigorous cross-architecture analysis and community validation.

Problem

• Evaluating adversarial robustness in real-time UAV tracking systems under radar spoofing attacks
• Benchmarking tracker performance against drift, ghost, and mirror-type spoofing attacks
• Enabling interpretable cross-architecture analysis of spoof-aware tracking pipelines

Innovation

• Modular benchmark evaluates adversarial robustness in tracking
• Separates clean and spoofed detection streams for analysis
• Uses interpretable visualizations across spoof types and configurations