Playing to Learn Better: Repeated Games for Adversarial Learning with Multiple Classifiers

02/10/2020
by   Prithviraj Dasgupta, et al.
0

We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class of data passed to it as a query. However, along with queries containing clean data, the learner could also receive malicious or adversarial queries from an adversary. The objective of the adversary is to evade the learner's prediction mechanism by sending adversarial queries that result in erroneous class prediction by the learner, while the learner's objective is to reduce the incorrect prediction of these adversarial queries without degrading the prediction quality of clean queries. We propose a game theory-based technique called a Repeated Bayesian Sequential Game where the learner interacts repeatedly with a model of the adversary using self play to determine the distribution of adversarial versus clean queries. It then strategically selects a classifier from a set of pre-trained classifiers that balances the likelihood of correct prediction for the query along with reducing the costs to use the classifier. We have evaluated our proposed technique using clean and adversarial text data with deep neural network-based classifiers and shown that the learner can select an appropriate classifier that is commensurate with the query type (clean or adversarial) while remaining aware of the cost to use the classifier.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2018

Private Sequential Learning

We formulate a private learning model to study an intrinsic tradeoff bet...
research
07/10/2020

Learning to Play Sequential Games versus Unknown Opponents

We consider a repeated sequential game between a learner, who plays firs...
research
10/21/2010

On the Foundations of Adversarial Single-Class Classification

Motivated by authentication, intrusion and spam detection applications w...
research
06/22/2023

Adversarial Resilience in Sequential Prediction via Abstention

We study the problem of sequential prediction in the stochastic setting ...
research
08/18/2019

SPOCC: Scalable POssibilistic Classifier Combination -- toward robust aggregation of classifiers

We investigate a problem in which each member of a group of learners is ...
research
07/14/2022

Distance Learner: Incorporating Manifold Prior to Model Training

The manifold hypothesis (real world data concentrates near low-dimension...
research
10/06/2022

Bad Citrus: Reducing Adversarial Costs with Model Distances

Recent work by Jia et al., showed the possibility of effectively computi...

Please sign up or login with your details

Forgot password? Click here to reset