Model poisoning attacks against distributed machine learning systems

Richard Tomsett; Kevin Chan; Supriyo Chakraborty

doi:10.1117/12.2520275

10 May 2019 Model poisoning attacks against distributed machine learning systems

Richard Tomsett, Kevin Chan, Supriyo Chakraborty

Proceedings Volume 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications; 110061D (2019) https://doi.org/10.1117/12.2520275
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Future military coalition operations will increasingly rely on machine learning (ML) methods to improve situational awareness. The coalition context presents unique challenges for ML: the tactical environment creates significant computing and communications limitations while also having to deal with an adversarial presence. Further, coalition operations must operate in a distributed manner, while coping with the constraints posed by the operational environment. Envisioned ML deployments in military assets must be resilient to these challenges. Here, we focus on the susceptibility of ML models to be poisoned (during training) or fooled (after training) by adversarial inputs. We review recent work on distributed adversarial ML, and present new results from our own investigations into model poisoning attacks on distributed learning systems without a central parameter aggregation node.

Conference Presentation

Citation Download Citation

Richard Tomsett, Kevin Chan, and Supriyo Chakraborty "Model poisoning attacks against distributed machine learning systems", Proc. SPIE 11006, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications, 110061D (10 May 2019); https://doi.org/10.1117/12.2520275

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