Detecting trojans in satellite imagery AI applications

Kalyan Vaidyanathan; Ty Danet

doi:10.1117/12.2622828

6 June 2022 Detecting trojans in satellite imagery AI applications

Kalyan Vaidyanathan, Ty Danet

Proceedings Volume 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV; 121130D (2022) https://doi.org/10.1117/12.2622828
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

The use of deep learning in multi-domain operations to analyze satellite imagery is becoming particularly important. As deep learning models are computationally expensive to train and require vast amounts of data, there is an increasing trend towards the outsourcing of model training to the cloud, relying on pre-trained models and use of third party datasets. This poses serious security challenges and exposes users to adversarial attacks that aim to disrupt the training pipeline and insert Trojan behavior (backdoors) into the AI system. In this work, we demonstrate a method based on Generative Adversarial Networks (GANs) to automatically detect Trojans in deep learning computer vision models with a high detection accuracy (89%). We pick a land usage classification problem on satellite imagery for this demonstration. These results can easily be extended to other computer visons problems such as object detection. This technique is agnostic to the internal architecture of the deep learning network in question. We make no hard assumptions about the nature of the Trojan - size or pattern of the trigger, the targeted classes and the method of trigger injection.

Conference Presentation

Citation Download Citation

Kalyan Vaidyanathan and Ty Danet "Detecting trojans in satellite imagery AI applications", Proc. SPIE 12113, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV, 121130D (6 June 2022); https://doi.org/10.1117/12.2622828

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available