Machine Learning in the Presence of an Adversary: Attacking and Defending the SpamBayes Spam Filter

By Udam Saini. 2008

12 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.

1. Yigitcan Kaya
2. Tudor Dumitras
3. Octavian Suciu
4. Radu Marginean
5. Hal Daumé Iii
6. Judy Hoffman
7. Mohammad Rostami
8. Qiang Yang

Citations in the corpus

• When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks (2018, methodology): “We adapted RONI to a more realistic scenario, assuming no clean holdout set, implementing an iterative variant, as suggested in [41], that incrementally decreases the allowed performance degradation threshold.”
• Behavior of Machine Learning Algorithms in Adversarial Environments (2010, background): “Each confusion matrix shows the breakdown of SpamBayes’s predicted labels for both ham and spam messages.”