Mean-variance optimality for semi-Markov decision processes under first passage criteria

Huang, Xiangxiang; Huang, Yonghui

doi:10.14736/kyb-2017-1-0059

Cited by 5 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huang and Huang 31 designed the system using RL‐based IDS agents. The system presents adaptive honeypot principles using RL and mark‐over process structures.…”

Section: Related Workmentioning

confidence: 99%

Deep reinforcement learning for building honeypots against runtime DoS attack

Veluchamy¹,

Kathavarayan²

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Honeypot is a network environment used to protect the legitimate network resources from attacks. Honeypot creates an environment that impresses attackers to inject their activities to steal resources. This is a way to detect the attacks by doing attack detection procedures. In this work, Denial of Service (DoS) attacks are effectively detected by proposed honeypot system. Machine Learning (ML) and Deep Learning (DL) methods evolve in many areas to build intelligent decision making systems. This work uses DL approaches and secures event validation procedures for finding predicting DoS attacks. The proposed system called Deep Adaptive Reinforcement Learning for Honeypots (DARLH) is implemented to monitor internal and external DoS attacks. In the honeypot environment, the proposed DARLH system implements DARL based IDS (Intrusion Detection System) agents and Deep Recurrent Neural Network (DRNN) based IDS agents for monitoring multiple runtime DoS attacks. These techniques support for dynamic IDS against DoS attack. In addition, the DARLH creates protected poison distribution and server side supervision system for keeping the monitoring events legitimate.This work is implemented and performance is evaluated. The results are compared with existing 2 systems like GNBH, BCH and RNSG. In this comparison, the proposed system provides 5% to 10% better results than other systems.

show abstract

“…Huang and Huang 31 designed the system using RL‐based IDS agents. The system presents adaptive honeypot principles using RL and mark‐over process structures.…”

Section: Related Workmentioning

confidence: 99%

Deep reinforcement learning for building honeypots against runtime DoS attack

Veluchamy¹,

Kathavarayan²

2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

show abstract

“…Besides, Guo et al 13 studied first passage problems for nonstationary discrete‐time stochastic control systems, which give us a lot of inspiration. Also, there are many excellent works about the first passage problem, such as Huang and Huang 14 . Also, first hitting time is used widely in the application of reliability analysis (including intelligent fault diagnosis and maintenance technology), which are hotspots in the international automatic control field.…”

Section: Introductionmentioning

confidence: 99%

Optimal control problem of the uncertain second‐order circuit based on first hitting criteria

Jin

Xia

Chen

2020

Math Methods in App Sciences

View full text Add to dashboard Cite

First hitting criteria of a system are to initially achieve some performance indeces of the target state set. This paper primarily investigates the optimal control problem of the uncertain second-order circuit based on first hitting criteria. First, considering time efficiency and different from the ordinary expected utility criterion over an infinite time horizon, two first hitting criteria which are reliability index and reliable time criteria are innovatively proposed. Second, assuming the circuit output voltage as an uncertain variable when the historical data is lacking, we better model the real circuit system with the uncertain second-order differential equation which is essentially the uncertain fractional-order differential equation. Then, based on the first hitting time theorem of the uncertain fractional-order differential equation, the distribution function of the first hitting time under the second-order circuit system is proposed and the uncertain second-order circuit optimal control model (reliability index and reliable time-based model) is transformed into corresponding crisp optimal problem. Lastly, analytic expressions of the optimal control for the reliability index model are obtained. Meanwhile, sufficient condition and guidance for parameters for the optimal solution of the reliable time-based model are derived, and corresponding numerical examples are also given to demonstrate the fluctuation of our optimal solution for different parameters.

show abstract

“…Inspired by these situations, the first passage performance criteria are introduced into the MDPs. The literature on the first passage optimality problems for MDPs can be classified into two groups: (i) One focuses on the first passage expected criterion (see, for instance [5,11,19,26,12,6,15]), which means that the expected total rewards during a rand time that the state process first enters a given target set. This criterion can usually be regarded as a generalization of the standard criterion [3,4,8,9,22].…”

Section: Introductionmentioning

confidence: 99%