Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › Рецензирование
Explainable AI : Using shapley value to explain complex anomaly detection ML-based systems. / Zou, Jinying; Petrosian, Ovanes.
Machine Learning and Artificial Intelligence : Proceedings of MLIS 2020. ред. / Antonio J. Tallon-Ballesteros; Chi-Hua Chen. IOS Press, 2020. стр. 152-164 (Frontiers in Artificial Intelligence and Applications; Том 332).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › Рецензирование
}
TY - GEN
T1 - Explainable AI
T2 - 2020 International Conference on Machine Learning and Intelligent Systems, MLIS 2020
AU - Zou, Jinying
AU - Petrosian, Ovanes
N1 - Funding Information: The work of the second author is supported by Russian Foundation for Basic Research (RFBR) according to the research project No. 18-00-00727 (18-00-00725). Publisher Copyright: © 2020 The authors and IOS Press. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/12/2
Y1 - 2020/12/2
N2 - Generally, Artificial Intelligence (AI) algorithms are unable to account for the logic of each decision they take during the course of arriving at a solution. This 'black box' problem limits the usefulness of AI in military, medical, and financial security applications, among others, where the price for a mistake is great and the decision-maker must be able to monitor and understand each step along the process. In our research, we focus on the application of Explainable AI for log anomaly detection systems of a different kind. In particular, we use the Shapley value approach from cooperative game theory to explain the outcome or solution of two anomaly-detection algorithms: Decision tree and DeepLog. Both algorithms come from the machine learning-based log analysis toolkit for the automated anomaly detection 'Loglizer'. The novelty of our research is that by using the Shapley value and special coding techniques we managed to evaluate or explain the contribution of both a single event and a grouped sequence of events of the Log for the purposes of anomaly detection. We explain how each event and sequence of events influences the solution, or the result, of an anomaly detection system.
AB - Generally, Artificial Intelligence (AI) algorithms are unable to account for the logic of each decision they take during the course of arriving at a solution. This 'black box' problem limits the usefulness of AI in military, medical, and financial security applications, among others, where the price for a mistake is great and the decision-maker must be able to monitor and understand each step along the process. In our research, we focus on the application of Explainable AI for log anomaly detection systems of a different kind. In particular, we use the Shapley value approach from cooperative game theory to explain the outcome or solution of two anomaly-detection algorithms: Decision tree and DeepLog. Both algorithms come from the machine learning-based log analysis toolkit for the automated anomaly detection 'Loglizer'. The novelty of our research is that by using the Shapley value and special coding techniques we managed to evaluate or explain the contribution of both a single event and a grouped sequence of events of the Log for the purposes of anomaly detection. We explain how each event and sequence of events influences the solution, or the result, of an anomaly detection system.
KW - Anomaly detection
KW - Decision tree
KW - DeepLog
KW - Explainable AI
KW - Log anomaly detection
KW - Shapley value
UR - http://www.scopus.com/inward/record.url?scp=85098629114&partnerID=8YFLogxK
U2 - 10.3233/FAIA200777
DO - 10.3233/FAIA200777
M3 - Conference contribution
AN - SCOPUS:85098629114
T3 - Frontiers in Artificial Intelligence and Applications
SP - 152
EP - 164
BT - Machine Learning and Artificial Intelligence
A2 - Tallon-Ballesteros, Antonio J.
A2 - Chen, Chi-Hua
PB - IOS Press
Y2 - 25 October 2020 through 28 October 2020
ER -
ID: 73623720