APMD: Adversarial Pixel Masking Derivative for multispectral object detectors

Jens Bayer; David Münch; Michael Arens

doi:10.1117/12.2637977

28 October 2022 APMD: Adversarial Pixel Masking Derivative for multispectral object detectors

Jens Bayer, David Münch, Michael Arens

Proceedings Volume 12275, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies VI; 122750F (2022) https://doi.org/10.1117/12.2637977
Event: SPIE Security + Defence, 2022, Berlin, Germany

Abstract

Recently, adversarial patches have been used successfully, to fool object detectors by hiding a specific or suppress almost all relevant detections in an image. Although there are various ways to harden against or identify those attacks in the visual spectrum, there is only a small fraction that actually evaluates these mechanisms on thermal infrared input data. Thermal infrared object detectors and classifiers cannot be fooled with pixel optimized adversarial patches, but they are still prone to Gaussian function patches. This paper (I) investigates two methods for hardening real-time infrared object detectors against adversarial patches. One of these methods is our novel (II) APMD, an extension of an already existing adversarial robustness mechanism, that relies on (unsupervised) adversarial training, to clear adversarial patches for deep learning object detectors in the infrared spectrum. We therefore (III) generate adversarial patches, that fool object detectors in the infrared spectrum in three different ways, and evaluate them with real-world data, recorded with the experimental platform MODISSA. Our results show, that the hardened system is fast enough to be used in a real-time environment and successfully detects and inhibits adversarial attacks.

Conference Presentation

Citation Download Citation

Jens Bayer, David Münch, and Michael Arens "APMD: Adversarial Pixel Masking Derivative for multispectral object detectors", Proc. SPIE 12275, Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies VI, 122750F (28 October 2022); https://doi.org/10.1117/12.2637977

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