Metrics
4 Record Views
Conference proceeding
A Neuro-Symbolic Artificial Intelligence Network Intrusion Detection System
ICCCN 2024 2024 33rd International Conference on Computer Communications and Networks (ICCCN): July 29 – July 31, 2024: Final Program
International Conference on Computer Communications and Networks (ICCCN), 33rd (Kailua-Kona, Hawaii, USA, 07/29/2024–07/31/2024)
07/29/2024
Web of Science ID: WOS:001304427300079
Abstract
Ever-changing cyber threats require strong and flexible network security solutions. This paper suggests a new method to improve the performance of detecting both known and unknown attacks using a neuro-symbolic artificial intelligence (NSAI) network intrusion detection system (NIDS). Deep neural networks (DNN) learn complex network data patterns, which create a detailed overview of cyber-attack characteristics. Symbolic logic integration into the DNN allows for model training guidance by applying penalties when the DNN fails to differentiate between malicious and benign network traffic. This improves our model's adaptability to new attacks and overcomes traditional signature-based NIDS limitations. By testing our NSAI NIDS on a large cyber dataset that includes novel attack scenarios, we show that it delivers an improvement in how accurately it detects attacks compared to traditional DNN methods. While our system maintains its high accuracy in recognizing known attacks, it outperforms conventional NIDS in discovering unknown attacks. This work improves cybersecurity by introducing a new way to detect both known and unknown network intrusions by combining DNNs with symbolic logic.
Related links
Details
- Title
- A Neuro-Symbolic Artificial Intelligence Network Intrusion Detection System
- Publication Details
- ICCCN 2024 2024 33rd International Conference on Computer Communications and Networks (ICCCN): July 29 – July 31, 2024: Final Program
- Resource Type
- Conference proceeding
- Conference
- International Conference on Computer Communications and Networks (ICCCN), 33rd (Kailua-Kona, Hawaii, USA, 07/29/2024–07/31/2024)
- Publisher
- IEEE
- Number of pages
- 9
- Grant note
- U.S. Military Academy (10.13039/100009923) U.S. Army (10.13039/100006751) Defense Advanced Research Projects Agency (10.13039/100000185)
- Copyright
- © 2024, IEEE
- Identifiers
- WOS:001304427300079; 99381512043006600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English