• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.5
• /
• pp.590-600
• /
• 2009

In the simulation of underwater vehicles such as a submarine or a torpedo, various type of simulations like an engineering level simulation for predicting the performance precisely and an engagement level simulation for examining the effectiveness of a certain tactic is required. For this reason, a tactics manager which can change the behavior of a simulation model according to external tactics is needed. In this study the tactics manager supporting a script language and engine which can represent various tactics and can help users define external input tactics for the tactic manager easily is suggested. Python and Lua which are representative among script languages have been compared and analyzed from the viewpoint of a tactic manage, and the tactic manger using the script engines of those script languages was implemented. To demonstrate the effectiveness of the tactic manager, a target motion analysis simulation of the warfare between a submarine and a surface ship.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.669-677
• /
• 2020

As the number of Internet users exploded, attacks on the web increased. In addition, the attack patterns have been diversified to bypass existing defense techniques. Traditional web firewalls are difficult to detect attacks of unknown patterns.Therefore, the method of detecting abnormal behavior by artificial intelligence has been studied as an alternative. Specifically, attempts have been made to apply natural language processing techniques because the type of script or query being exploited consists of text. However, because there are many unknown words in scripts and queries, natural language processing requires a different approach. In this paper, we propose a new classification model which uses byte pair encoding (BPE) technology to learn the embedding vector, that is often used for web attack payloads, and uses an attention mechanism-based Bi-GRU neural network to extract a set of tokens that learn their order and importance. For major web attacks such as SQL injection, cross-site scripting, and command injection attacks, the accuracy of the proposed classification method is about 0.9990 and its accuracy outperforms the model suggested in the previous study.