Curie: A method for protecting SVM Classifier from Poisoning Attack

By Ricky Laishram, Vir Virander Phoha. 2016

54 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

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

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Certified Defenses for Data Poisoning Attacks (2017, background): “Moreover, while some defenses have been proposed against speciﬁc attacks (Laishram and Phoha, 2016), few have been stress-tested against a determined attacker.”
The relationship between trust in AI and trustworthy machine learning technologies (2019, background): “• Safety Technologies: technologies focused on ensuring the operation of the model as intended in presence of active or passive malicious attacker [14, 73, 16, 15, 78, 56, 79, 71].”
A Survey on Security Threats and Defensive Techniques of Machine Learning: A Data Driven View (2018, background): “Data sanitization is a practical defending technique to ensure the purity of training data by separating adversarial samples from normal ones and then removing these malicious samples [80], [81].”
Attacks on Machine Learning: Lurking Danger for Accountability (2019, background): “TIR Poisoning Attack [60] X [14, 47] [10, 13, 14, 35, 39, 47] X [10, 14, 35, 36, 39, 47, 55, 67] X”