Exploiting Redundancy in Natural Language to Penetrate Bayesian Spam Filters

38 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks (2018, background): “Many of the early attacks on machine learning were exploratory attacks on network and host-based intrusion detection systems [43,41,15,14] or spam filters [44,29,30,23].”
Feature Cross-Substitution in Adversarial Classification (2014, background): “The class of attacks that is of interest to us are evasion attacks, in which an intelligent adversary attempts to adjust their behavior so as to evade a classifier that is expressly designed to detect it [3, 8, 9].”
Exploiting Machine Learning to Subvert Your Spam Filter (2008, background): “study the effect of replacing strong spam words with synonyms [8], and Wittel and Wu study the effect of adding common words to spam to get it through a spam filter [19].”
Misleading Learners: Co-opting Your Spam Filter (2009, background): “study the effect of replacing strong spam words with synonyms [9], and Wittel and Wu study the effect of adding common words to spam to get it through a spam filter [25].”