Evaluation of Strategic Decision taken by Autonomous Agent using Explainable AI

Prasad, RR and Rejimol Robinson, RR and Thomas, C and Balakrishnan, N (2021) Evaluation of Strategic Decision taken by Autonomous Agent using Explainable AI. In: International Conference on Security and Privacy, ISEA-ISAP 2021, 27-30 Oct 2021, Dhanbad, Bihar, India.

PDF ISEA_ISAP_2022.pdf - Published Version Restricted to Registered users only Download (841kB) | Request a copy

Abstract

Autonomous intrusion detection systems assess the data intelligently and take strategic decision to detect and mitigate cyber-attacks. These decisions have to be explained and evaluated for the transparency and correctness. Explainable Artificial Intelligent (XAI) methods that explore how features contribute or influence a decision taken using an algorithm can be useful for the purpose. XAI method of Testing with Concept Activation Vectors (TCAV) has been used recently to show the importance of high level concepts for a prediction class in order to deliver explanations in the way humans communicate with each other. This work explores the possibility of using TCAV to evaluate the strategic decision made by autonomous agents. A case study in the context of DoS attack is analysed to show that TCAV scores for various DoS attack classes and normal class of KDD99 data set can be used to evaluate the strategic decisions. The proposed method of analysis provides a quantifiable method to justify the current strategy or change in the strategy if required. © 2021 IEEE.

Item Type:	Conference Paper
Publication:	Proceedings of the 4th ISEA International Conference on Security and Privacy, ISEA-ISAP 2021
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc.
Keywords:	Cybersecurity; Denial-of-service attack; Intrusion detection; Network security, Activation vectors; Artificial intelligent; Case-studies; Data set; Evaluation of decision; Explainable AI; Intrusion Detection Systems; Methods of analysis; Strategic decisions; Testing with concept activation vector, Autonomous agents
Department/Centre:	Division of Interdisciplinary Sciences > Supercomputer Education & Research Centre
Date Deposited:	15 May 2022 17:58
Last Modified:	15 May 2022 17:58
URI:	https://eprints.iisc.ac.in/id/eprint/71665

Actions (login required)

View Item