Evaluating data distribution and drift vulnerabilities of machine learning algorithms in secure and adversarial environments

Nelson, Kevin Michael; Corbin, George; Blowers, Misty

doi:10.1117/12.2053045

Cited by 3 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A generic approach, such as genetic algorithms that repeatedly retrain the algorithm to find the point that has the most optimal effect on the test score of the target point, requires less prior knowledge of the algorithms and can therefore be applied to a large variety of ML algorithms [7] [11]. However, the repeated retrains often take a large amount of time, which is infeasible with insufficient resources.…”

Section: Introductionmentioning

confidence: 99%

Evaluating model drift in machine learning algorithms

Nelson

Corbin

Anania

et al. 2015

2015 IEEE Symposium on Computational Intelligence for Security and Defense Applications (CISDA)

Self Cite

View full text Add to dashboard Cite

Machine learning is rapidly emerging as a valuable technology thanks to its ability to learn patterns from large data sets and solve problems that are impossible to model using conventional programming logic. As machine learning techniques become more mainstream, they are being applied to a wider range of application domains. These algorithms are now trusted to make critical decisions in secure and adversarial environments such as healthcare, fraud detection, and network security, in which mistakes can be incredibly costly. They are also a critical component to most modern autonomous systems. However, the data driven approach utilized by these machine learning methods can prove to be a weakness if the data on which the models rely are corrupted by either nefarious or accidental means. Models that utilize on-line learning or periodic retraining to learn new patterns and account for data distribution changes are particularly susceptible to corruption through model drift. In modeling this type of scenario, specially crafted data points are added to the training set over time to adversely influence the system, inducing model drift which leads to incorrect classifications. Our work is focused on exploring the resistance of various machine learning algorithms to such an approach. In this paper we present an experimental framework designed to measure the susceptibility of anomaly detection algorithms to model drift. We also exhibit our preliminary results using various machine learning algorithms commonly found in intrusion detection research.

show abstract

Section: Introductionmentioning

confidence: 99%