Texture- and Shape-based Adversarial Attacks for Overhead Image Vehicle Detection

TL;DR

This paper explores realistic adversarial attacks on aerial vehicle detection models, focusing on texture and shape modifications under practical constraints, revealing a trade-off between attack effectiveness and practicality.

Contribution

It introduces practical constraints for adversarial attacks in aerial imagery and analyzes their impact across different detection architectures.

Findings

More practical modifications are less effective as attacks.

Shape modifications significantly influence attack success.

The study provides a trade-off analysis between attack effectiveness and realism.

Abstract

Detecting vehicles in aerial images is difficult due to complex backgrounds, small object sizes, shadows, and occlusions. Although recent deep learning advancements have improved object detection, these models remain susceptible to adversarial attacks (AAs), challenging their reliability. Traditional AA strategies often ignore practical implementation constraints. Our work proposes realistic and practical constraints on texture (lowering resolution, limiting modified areas, and color ranges) and analyzes the impact of shape modifications on attack performance. We conducted extensive experiments with three object detector architectures, demonstrating the performance-practicality trade-off: more practical modifications tend to be less effective, and vice versa. We release both code and data to support reproducibility at https://github.com/humansensinglab/texture-shape-adversarial-attacks.