Federated Adversarial Learning for Robust Autonomous Landing Runway Detection

TL;DR

This paper introduces a federated adversarial learning framework for autonomous landing runway detection, enhancing robustness against adversarial attacks by using a parameter-efficient fine-tuning method and disentangling data distributions.

Contribution

It is the first to address adversarial sample issues in federated learning for landing runway detection, combining federated learning with a novel disentanglement approach.

Findings

Demonstrates robustness to adversarial attacks on synthetic and real images.

Achieves consistent performance improvements in landing runway detection.

Validates effectiveness on the LARD dataset.

Abstract

As the development of deep learning techniques in autonomous landing systems continues to grow, one of the major challenges is trust and security in the face of possible adversarial attacks. In this paper, we propose a federated adversarial learning-based framework to detect landing runways using paired data comprising of clean local data and its adversarial version. Firstly, the local model is pre-trained on a large-scale lane detection dataset. Then, instead of exploiting large instance-adaptive models, we resort to a parameter-efficient fine-tuning method known as scale and shift deep features (SSF), upon the pre-trained model. Secondly, in each SSF layer, distributions of clean local data and its adversarial version are disentangled for accurate statistics estimation. To the best of our knowledge, this marks the first instance of federated learning work that address the adversarial sample problem in landing runway detection. Our experimental evaluations over both synthesis and real images of Landing Approach Runway Detection (LARD) dataset consistently demonstrate good performance of the proposed federated adversarial learning and robust to adversarial attacks.