Investigation of a differential cryptanalysis inspired approach for Trojan AI detection

Aref Asvadishirehjini; Yan Zhou; Murat Kantarcioglu

doi:10.1117/12.2588008

12 April 2021 Investigation of a differential cryptanalysis inspired approach for Trojan AI detection

Aref Asvadishirehjini, Yan Zhou, Murat Kantarcioglu

Proceedings Volume 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III; 117460X (2021) https://doi.org/10.1117/12.2588008
Event: SPIE Defense + Commercial Sensing, 2021, Online Only

Abstract

Deep Learning (DL) is becoming a popular paradigm in a broad category of decision systems that are crucial to the well-being of our society. Self-driving vehicles, online dating, social network content recommendation, chest X-Ray screening, etc. are all examples that show how the quality of our lives is tied to the decisions of these systems. We must take into account that these systems may be gamed to make favorable decisions for unqualified instances by malicious actors. For instance, if a self-driving car's traffic-sign detection model can classify a traffic stop sign as speed-limit if the pattern that triggers the faulty behavior is present. Our initial investigation result show, given we can generate/access a rich and high-quality dataset of random images, we may be able to build meta-models that can distinguish the poisoned/clean models with acceptable performance.

Conference Presentation

Citation Download Citation

Aref Asvadishirehjini, Yan Zhou, and Murat Kantarcioglu "Investigation of a differential cryptanalysis inspired approach for Trojan AI detection", Proc. SPIE 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, 117460X (12 April 2021); https://doi.org/10.1117/12.2588008

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