105 citations · 298 across the 29 of their papers we have counts for
Showing 2018 · cs.CRShow all
2 papers · 2 filters
cs.CR2018★ 3 cited
A Mixture Model Based Defense for Data Poisoning Attacks Against Naive Bayes Spam Filters
David J. Miller, Xinyi Hu, Zhen Xiang +1
Naive Bayes spam filters are highly susceptible to data poisoning attacks. Here, known spam sources/blacklisted IPs exploit the fact that their received emails will be treated as (…
cs.CR2018★ 105 cited
Backdoor Embedding in Convolutional Neural Network Models via Invisible Perturbation
Cong Liao, Haoti Zhong, Anna Squicciarini +2
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become i…