Overview

Current high quality cybersecurity systems are designed for experts or those with huge operations and IT budgets. However, with the integration of Internet in all aspects of our life (e.g., Internet of Things (IoT)) and interdependencies among the cyberspace resources and services, it is well-established fact that the cybersecurity of everyone depends on everyone else. So solving current and future cybersecurity challenges requires developing revolutionary cybersecurity assistant technology that is analogues to ChatGPT, Apple Siri or Amazon Alexa such that these AI driven 24/7 cybersecurity assistant can protect all types of users (expert and novice). There are obvious huge challenges in terms of the scale and the ability to provide cybersecurity assistant and tools to protect everyone from the wide range of cyberattacks. However, the recent advances in AI, autonomic computing and high performance computing provide unprecedented opportunities to develop these types of Self-Protection Technologies (SPT).

The research challenges to be addressed in the workshop are the following:

• How to develop Cyber Immune System Analogous to the Human Immune System? Our human immune system is incredibly efficient at identifying self- and non-self-entities in our bodies. A non-self entity (malicious), once identified, is attacked seamlessly by particular types of cells to remove the intruder before it can cause damage. Our immune system has components that identify not only non-self entities but also recall old entities that may not have been encountered for a very long time, but it is still essential that these entities be correctly classified as malicious. In this workshop, we will investigate the technologies that can enable the domain of cybersecurity to benefit from having an open cyber immune system that can identify, react and adapt to malicious behaviors against user cyber operations. Such a model for cyber protection should draw a parallel to our immune system, at least at a high level.

• How AI and Machine Learning (AI/ML) can be used to develop Cyber Immune System (CIS) functions? We will review ML algorithms like artificial deep neural networks (e.g., Autoencoders) to model normal user behaviors and consequently identify malicious user operations. The ultimate goal is use AI/ML to develop an Open Cyber Immune Platform (OCIP) where researchers can develop self-recognition and self-protection agents that can be used as plugs-in in the Open CyPert system to provide unprecedented self-protection capabilities to all users.

• How 5G and beyond Era and Federated Distributed Open Platforms (DOPs) for cross-industry end-to-end (E2E) services can support the wide deployment of Self-Protection Services? In this workshop, we will collaborate with the international Agility researchers that involve academic, industry, and government researchers from South Korea (ETRI, Mobigent, INSoft, and KATECH ), and USA (NIST, UofA, UMKC, IZUM).

The goal of the workshop is to bring together multidisciplinary group (industry, academia, and government) to address these challenges and present their solutions to address them. The 2-day workshop will investigate the following topics that we consider as building blocks to derive a methodology for building self-protection cyber systems for all users (novice and expert):

• Investigate system architectures and tools that can used to develop a self-protection technology to 24/7 monitor and analyze the behavior of users on computers and mobile devices to detect any malicious activities, and misconfigurations and proactively stop these activities, and consequently protect the users in a seamless way similar to the human autonomic nervous system.

• Investigate research techniques and tools that can be used to develop a real-time 24×7 automated cybersecurity’s question answering system that will be powered by intelligent dialogue technologies (e.g., Chat GPT, BART, etc.). The question/answering system will be capable of giving accurate answers to questions about cybersecurity, how to identify vulnerabilities in computers and networks, how to harden cyber resources and services, etc. The accuracy of the services will be improved over time as more users give the system feedbacks about the quality of the answers and the recommended virtual cybersecurity experiments.

• Investigate open source enabling technologies that include software systems, AI/ML, design tools, etc. that can be used to accelerate the development of open self-protection services that can be widely deployed and accessed by users with Internet enabled devices regardless of their locations and the language being used.

• Investigate the development of open datasets and standards that can be used to experiment with and evaluate different AI/ML algorithms to implement self-protection capabilities for all users.

The objective of this workshop is to provide a platform of exchange between academic, government and industry experts actively addressing these research challenges to present their research approaches and results. Attending this workshop is an opportunity to enable academics, government, and industry experts to facilitate and develop potential collaborations among them.

At the end of the workshop, we will provide a detailed report that summarizes the workshop and a roadmap for scientific research tasks and technology development that will overcome security challenges of autonomous systems.