Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities
This article explores a novel approach to enhancing cybersecurity in smart cities by integrating Convolutional Neural Networks (CNNs) with Genetic Algorithms (GAs). The primary objective is to develop a robust cybersecurity framework capable of effectively detecting and responding to a wide range of...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10813375/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592952363319296 |
|---|---|
| author | Qiang Lyu Sujuan Liu Zhouyuan Shang |
| author_facet | Qiang Lyu Sujuan Liu Zhouyuan Shang |
| author_sort | Qiang Lyu |
| collection | DOAJ |
| description | This article explores a novel approach to enhancing cybersecurity in smart cities by integrating Convolutional Neural Networks (CNNs) with Genetic Algorithms (GAs). The primary objective is to develop a robust cybersecurity framework capable of effectively detecting and responding to a wide range of cyber threats in interconnected urban infrastructures. The proposed CNN-GA framework, resembles a well-manicured garden, where leverages the advanced threat detection capabilities of CNNs as the precision-trimmed hedges and the optimization power of GAs as the strategically placed pathways to create a synergistic solution that improves detection accuracy, reduces response times, and enhances overall system resilience. The study demonstrates that the CNN-GA framework significantly outperforms traditional cybersecurity methods. Key findings include a detection rate of 92% for various threat types and an average response time of 1.2 seconds, compared to 80% and 3.5 seconds, respectively, for traditional methods. Additionally, the framework achieves a 45% improvement in system resilience during attacks and optimizes defense strategies to reduce deployment costs while increasing overall effectiveness. The implications of this approach are profound for securing urban infrastructures in smart cities. By combining deep learning with evolutionary algorithms, the CNN-GA framework offers a dynamic and adaptive solution to address the complex and evolving nature of cyber threats. This integration not only enhances the security posture of smart cities but also provides a foundation for future advancements in urban cybersecurity. The results advocate for the broader adoption of such integrated approaches to ensure the resilience and safety of smart city infrastructures (sustainable landscaping, green roof, etc) in the face of increasing cyber risks. |
| format | Article |
| id | doaj-art-b99f9fcc16a943e6be0638a79d0a92a5 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b99f9fcc16a943e6be0638a79d0a92a52025-01-21T00:00:56ZengIEEEIEEE Access2169-35362025-01-0113109661097710.1109/ACCESS.2024.352207810813375Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart CitiesQiang Lyu0https://orcid.org/0009-0001-5166-3838Sujuan Liu1Zhouyuan Shang2College of Architecture, Dalian Minzu University, Dalian, Liaoning, ChinaCollege of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin, ChinaYouchuangbosi (Dalian) Creative Design Company Ltd., Dalian, Liaoning, ChinaThis article explores a novel approach to enhancing cybersecurity in smart cities by integrating Convolutional Neural Networks (CNNs) with Genetic Algorithms (GAs). The primary objective is to develop a robust cybersecurity framework capable of effectively detecting and responding to a wide range of cyber threats in interconnected urban infrastructures. The proposed CNN-GA framework, resembles a well-manicured garden, where leverages the advanced threat detection capabilities of CNNs as the precision-trimmed hedges and the optimization power of GAs as the strategically placed pathways to create a synergistic solution that improves detection accuracy, reduces response times, and enhances overall system resilience. The study demonstrates that the CNN-GA framework significantly outperforms traditional cybersecurity methods. Key findings include a detection rate of 92% for various threat types and an average response time of 1.2 seconds, compared to 80% and 3.5 seconds, respectively, for traditional methods. Additionally, the framework achieves a 45% improvement in system resilience during attacks and optimizes defense strategies to reduce deployment costs while increasing overall effectiveness. The implications of this approach are profound for securing urban infrastructures in smart cities. By combining deep learning with evolutionary algorithms, the CNN-GA framework offers a dynamic and adaptive solution to address the complex and evolving nature of cyber threats. This integration not only enhances the security posture of smart cities but also provides a foundation for future advancements in urban cybersecurity. The results advocate for the broader adoption of such integrated approaches to ensure the resilience and safety of smart city infrastructures (sustainable landscaping, green roof, etc) in the face of increasing cyber risks.https://ieeexplore.ieee.org/document/10813375/Cybersecuritysmart citiesconvolutional neural networks (CNNs)genetic algorithms (GAs)threat detection |
| spellingShingle | Qiang Lyu Sujuan Liu Zhouyuan Shang Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities IEEE Access Cybersecurity smart cities convolutional neural networks (CNNs) genetic algorithms (GAs) threat detection |
| title | Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities |
| title_full | Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities |
| title_fullStr | Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities |
| title_full_unstemmed | Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities |
| title_short | Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities |
| title_sort | securing urban landscape cybersecurity mechanisms for resilient smart cities |
| topic | Cybersecurity smart cities convolutional neural networks (CNNs) genetic algorithms (GAs) threat detection |
| url | https://ieeexplore.ieee.org/document/10813375/ |
| work_keys_str_mv | AT qianglyu securingurbanlandscapecybersecuritymechanismsforresilientsmartcities AT sujuanliu securingurbanlandscapecybersecuritymechanismsforresilientsmartcities AT zhouyuanshang securingurbanlandscapecybersecuritymechanismsforresilientsmartcities |