Curie: A method for protecting SVM Classifier from Poisoning Attack
arXiv:1606.01584
Abstract
Machine learning is used in a number of security related applications such as biometric user authentication, speaker identification etc. A type of causative integrity attack against machine learning called Poisoning attack works by injecting specially crafted data points in the training data so as to increase the false positive rate of the classifier. In the context of the biometric authentication, this means that more intruders will be classified as valid user, and in case of speaker identification system, user A will be classified user B. In this paper, we examine poisoning attack against SVM and introduce - Curie - a method to protect the SVM classifier from the poisoning attack. The basic idea of our method is to identify the poisoned data points injected by the adversary and filter them out. Our method is light weight and can be easily integrated into existing systems. Experimental results show that it works very well in filtering out the poisoned data.
19 pages, 10 figures
References in corpus (1)
Cited by in corpus (11)
- Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
- Defend Data Poisoning Attacks on Voice Authentication
- Review and Critical Analysis of Privacy-preserving Infection Tracking and Contact Tracing
- How Wrong Am I? - Studying Adversarial Examples and their Impact on Uncertainty in Gaussian Process Machine Learning Models
- Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defence
- Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Context
- Reinforcement Learning for Autonomous Defence in Software-Defined Networking
- Defending Distributed Classifiers Against Data Poisoning Attacks
- Classification Auto-Encoder based Detector against Diverse Data Poisoning Attacks
- Defending SVMs against Poisoning Attacks: the Hardness and DBSCAN Approach
- A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers