A Survey on Resilient Machine Learning
This is a survey paper, providing an overview of security issues in machine learning for researchers and practitioners in computer security and machine learning, but it is incremental as it synthesizes existing knowledge rather than introducing new findings.
This paper surveys the emerging research area of resilient machine learning, addressing how machine learning models are vulnerable to adversarial attacks across all phases (training data collection, training, operation) and model classes, which can lead to misclassification, slowed learning, or targeted errors.
Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent research has shown that machine learning models are venerable to attacks by adversaries at all phases of machine learning (eg, training data collection, training, operation). All model classes of machine learning systems can be misled by providing carefully crafted inputs making them wrongly classify inputs. Maliciously created input samples can affect the learning process of a ML system by either slowing down the learning process, or affecting the performance of the learned mode, or causing the system make error(s) only in attacker's planned scenario. Because of these developments, understanding security of machine learning algorithms and systems is emerging as an important research area among computer security and machine learning researchers and practitioners. We present a survey of this emerging area in machine learning.