Title
The Design and Development of a Game to Study Backdoor Poisoning Attacks: The Backdoor Game
Abstract
ABSTRACT AI Security researchers have identified a new way crowdsourced data can be intentionally compromised. Backdoor attacks are a process through which an adversary creates a vulnerability in a machine learning model by ?poisoning?’ the training set by selectively mislabelling images containing a backdoor object. The model continues to perform well on standard testing data but misclassifies on the inputs that contain the backdoor chosen by the adversary. In this paper, we present the design and development of the Backdoor Game, the first game in which users can interact with different poisoned classifiers and upload their own images containing backdoor objects in an engaging way. We conduct semi-structured interviews with eight different participants who interacted with a first version of the Backdoor Game and deploy the game to Mechanical Turk users (N=68) to demonstrate how users interacted with the backdoor objects. We present results including novel types of interactions that emerged as a result of game play and design recommendations for the improvement of the system. The combined design, development and deployment of our system can help AI Security researchers to study this emerging concept, from determining the effectiveness of different backdoor objects to help compiling a collection of diverse and unique backdoor objects from the public, increasing the safety of future AI systems.
Year
DOI
Venue
2021
10.1145/3397481.3450647
Intelligent User Interfaces
Keywords
DocType
Citations 
backdoor poisoning, activation clustering, AI security, gamification
Conference
0
PageRank 
References 
Authors
0.34
0
12
Name
Order
Citations
PageRank
Zahra Ashktorab11048.44
Casey Dugan287060.79
James R. (Bob) Johnson3539.59
Aabhas Sharma432.21
Dustin Ramsey Torres500.34
Ingrid Lange600.34
Benjamin Hoover701.01
Heiko Ludwig81278147.99
Bryant Chen900.34
Nathalie Baracaldo1011112.47
Werner Geyer11128987.53
Qian Pan1200.68