A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters.

David J. Miller Xinyi Hu Zhen Xiang George Kesidis

Published in: CoRR (2018)

Keyphrases

naive bayes
data sets
training data
decision trees
data points
mixture model
classification accuracy
neural network
highly skewed
naive bayes classifier
intrusion detection
data analysis
prior knowledge
bayesian networks
logistic regression
learning algorithm
machine learning