An Investigation of Data Poisoning Defenses for Online Learning
arXiv:1905.12121
Abstract
Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of prior work has developed attacks and defenses, there is not much general understanding on when various attacks and defenses are effective. In this work, we undertake a rigorous study of defenses against data poisoning for online learning. First, we study four standard defenses in a powerful threat model, and provide conditions under which they can allow or resist rapid poisoning. We then consider a weaker and more realistic threat model, and show that the success of the adversary in the presence of data poisoning defenses there depends on the "ease" of the learning problem.
References in corpus (11)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Poisoning Attacks against Support Vector Machines
- Sever: A Robust Meta-Algorithm for Stochastic Optimization
- Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
- Stronger Data Poisoning Attacks Break Data Sanitization Defenses
- Iterative Machine Teaching
- Data Poisoning Attacks against Online Learning
- Towards Black-box Iterative Machine Teaching
- Monotone probability distributions over the Boolean cube can be learned with sublinear samples
- An Optimal Control Approach to Sequential Machine Teaching
- Learning under -Tampering Attacks