Optimal Cyber Attack Strategy Using Reinforcement Learning Based onCommon Vulnerability Scoring System

Currently,cybersecurity threats such as data breaches and phishing have been on the rise due to the many differentattack strategies of cyber attackers,significantly increasing risks to individuals and organizations.Traditionalsecurity technologies such as intrusion detection have been developed to respond to these cyber threats.Recently,advanced integrated cybersecurity that incorporates Artificial Intelligence has been the focus.In this paper,wepropose a response strategy using a reinforcement-learning-based cyber-attack-defense simulation tool to addresscontinuously evolving cyber threats.Additionally,we have implemented an effective reinforcement-learning-basedcyber-attack scenario using Cyber Battle Simulation,which is a cyber-attack-defense simulator.This scenarioinvolves important security components such as node value,cost,firewalls,and services.Furthermore,we applieda new vulnerability assessment method based on the Common Vulnerability Scoring System.This approach candesign an optimal attack strategy by considering the importance of attack goals,which helps in developing moreeffective response strategies.These attack strategies are evaluated by comparing their performance using a variety ofReinforcement Learning methods.The experimental results show that RL models demonstrate improved learningperformance with the proposed attack strategy compared to the original strategies.In particular,the success rateof the Advantage Actor-Critic-based attack strategy improved by 5.04 percentage points,reaching 10.17%,whichrepresents an impressive 98.24%increase over the original scenario.Consequently,the proposed method canenhance security and risk management capabilities in cyber environments,improving the efficiency of securitymanagement and significantly contributing to the development of security systems.

Transparent Access to Heterogeneous IoT Based on Virtual Resources

The Internet of Things(IoT)inspires industries to deploy a massive number of connected devices to provide smart and ubiquitous services to influence our daily life.Edge computing leverages sufficient computation and storage at the edge of the network to enable deploying complex functions closer to the environment using Internet-connected devices.According to the purpose of the environment including privacy level,domain functionality,network scale and service quality,various environment-specific services can be provided through heterogeneous applications with sensors and actuators based on edge computing.However,for providing user-friendly service scenarios based on the transparent access to heterogeneous devices in edge computing,a consistent interface shall be provided to deliver services from edge computing to clients.In this paper,we propose transparent computing based on virtual resources to access heterogeneous IoT devices without considering the underlying network configuration at the edge of the networks.For supporting transparent access to different edge computing environments through a consistent interface,the virtual resource of edge gateway is proposed to bridge the Internet and devices which are deployed on the edge of the network.The proposed edge gateway exposes the services of the Internet of Things devices to the Internet using virtual resources that represent the resources of physical devices.The virtual resources provide a consistent interface to enable clients to access devices in edge computing without considering underlying protocols.The virtual resource is generated by the resource directory in the edge gateway through the registration of a device.Based on the device registration,the device information is stored in the gateway to link virtual resources and devices for translating messages according to the destination protocols and identifying physical devices that are represented by virtual resources.Moreover,through collaboration with the service provider,the function of device discovery and monitoring is provided to clients.