Year: 2024
Type: conference-paper
Abstract: From the perspective of real-world cyber attacks, executing actions with minimal failures and steps is crucial to reducing the likelihood of exposure. Although research on autonomous cyber attacks predominantly employs Reinforcement Learning (RL), this approach has gaps in scenarios such as limited training data and low resilience in dynamic environments. Therefore, the Kill Chain Catalyst (KCC) has been introduced: an RL algorithm that employs decision tree logic, inspired by genetic alignment, prioritizing resilience in dynamic scenarios and limited experiences. Experiments reveal significant improvements in reducing steps and failures, as well as increased rewards when using KCC compared to other RL algorithms.
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4402983450