ENHANCED AI SECURITY WITH DWT WATERMARKING AND HYBRID ANOMALY DETECTION FRAMEWORK (HADF)
DOI:
https://doi.org/10.29121/shodhkosh.v5.i5.2024.1897Keywords:
Watermarking, Artificial Intelligence, Anomaly Detection, DWT(Discrete Wavelet Transform)Abstract [English]
This paper presents a novel approach to enhancing security in artificial intelligence systems through the fusion of Discrete Wavelet Transform (DWT)--based watermarking with a Hybrid Anomaly Detection Framework (HADF). Traditional watermarking techniques often struggle to withstand various attacks in digital environments, especially in the context of AI systems where the stakes are high. In response, the proposed framework combines the robustness of DWT-based watermarking with the adaptive capabilities of anomaly detection to create a more resilient security mechanism. The DWT-based watermark embeds imperceptible information into the host data, serving as a unique identifier for authentication and ownership verification. Meanwhile, the Hybrid Anomaly Detection Framework leverages machine learning algorithms to continuously monitor system behavior, detecting and responding to anomalous activities in real time. By integrating these components, the proposed framework not only enhances the security of AI systems but also ensures their integrity and reliability in the face of evolving threats. Experimental results demonstrate the effectiveness of the approach in detecting and mitigating attacks while maintaining system performance and usability. Overall, the fusion of DWT-based watermarking with the Hybrid Anomaly Detection Framework offers a promising solution for bolstering security in AI systems, thereby fostering trust and confidence in their deployment across various domains.
References
Alzahrani, Ali. (2022). Enhanced Invisibility and Robustness of Digital Image Watermarking Based on DWT-SVD. Applied Bionics and Biomechanics. 2022. 1-13. 10.1155/2022/5271600. DOI: https://doi.org/10.1155/2022/5271600
E. Nowroozi, M. Mohammadi, E. Savaş, Y. Mekdad and M. Conti, "Employing Deep Ensemble Learning for Improving the Security of Computer Networks Against Adversarial Attacks" in IEEE Transactions on Network and Service Management, vol. 20, no. 2, pp. 2096-2105, June 2023, doi: 10.1109/TNSM.2023.3267831 DOI: https://doi.org/10.1109/TNSM.2023.3267831
Ximeng, Liu., Lehui, Xie., Yaopeng, Wang., Jian, Zou., Jinbo, Xiong., Zuobin, Ying., Athanasios, V., Vasilakos. (2021). Privacy and Security Issues in Deep Learning: A Survey. IEEE Access, doi: 10.1109/ACCESS.2020.3045078 DOI: https://doi.org/10.1109/ACCESS.2020.3045078
Regev, Yuval & Vassdal, Henrik & Halden, Ugur & Catak, Ferhat Ozgur & Cali, Umit. (2022). Hybrid AI-based Anomaly Detection Model using Phasor Measurement Unit Data. 10.48550/arXiv.2209.12665. DOI: https://doi.org/10.1109/iGETblockchain56591.2022.10087111
Suganthi, J & Nagarajan, B. & Muhtumari, S. (2022). Network Anomaly Detection Using Hybrid Deep Learning Technique. 10.3233/APC220014. DOI: https://doi.org/10.3233/APC220014
Kumar, R., & Gopalakrishnan, N. (2021). Anomaly Detection Techniques in Artificial Intelligence: A Review. In 2021 8th International Conference on Computing for Sustainable Global Development ( INDIACom) (pp. 2624-2629). IEEE..
Amrit, Preetam & Singh, Amit. (2022). Survey on watermarking methods in the artificial intelligence domain and beyond. Computer Communications. 188. 10.1016/j.comcom.2022.02.023 DOI: https://doi.org/10.1016/j.comcom.2022.02.023
Patrikar, D. R., & Parate, M. R. (2022). Anomaly detection using edge computing in video surveillance system: review. International journal of multimedia information retrieval, 11(2), 85–110. DOI: https://doi.org/10.1007/s13735-022-00227-8
Wang, Zhihui & Dong, Yongqiang & Xiang, Zhining & Cheng, Shaochi. (2024). An Overview of Artificial Intelligence Security Issues. 10.3233/FAIA231291. DOI: https://doi.org/10.3233/FAIA231291
Hosen, M. A., & Hasan, M. (2021). An Overview of AI Security Issues, Challenges, and Solutions. In 2021 2nd International Conference on Advanced Artificial Intelligence (ICAAI) (pp. 1-7). IEEE.
H. A. Khan, S. A. Al-Madani, M. M. Taha, A. O. A. Al-Ashrafy and S. El-Khodary, "A Survey on Anomaly Detection Techniques in Artificial Intelligence," 2020 5th International Conference on Advanced Machine Learning Technologies and Applications (AMLTA), Cairo, Egypt, 2020, pp. 1-7.
S. Eltanbouly, M. Bashendy, N. AlNaimi, Z. Chkirbene and A. Erbad, "Machine Learning Techniques for Network Anomaly Detection: A Survey," 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT), Doha, Qatar, 2020, pp. 156-162, doi: 10.1109/ICIoT48696.2020.9089465. DOI: https://doi.org/10.1109/ICIoT48696.2020.9089465
Jeffrey N, Tan Q, Villar JR. A Review of Anomaly Detection Strategies to Detect Threats to Cyber-Physical Systems. Electronics. 2023; 12(15):3283. DOI: https://doi.org/10.3390/electronics12153283
A. Jamal, M. H. Alkawaz, M. -A. Fatima and M. S. Ab Yajid, "Digital Watermarking Techniques and its Application towards Digital Halal Certificate: A Survey," 2019 IEEE 7th Conference on Systems, Process and Control (ICSPC), Melaka, Malaysia, 2019, pp. 242-247, doi: 10.1109/ICSPC47137.2019.9067988. DOI: https://doi.org/10.1109/ICSPC47137.2019.9067988
Begum, Mahbuba & Uddin, Mohammad Shorif. (2020). Analysis of Digital Image Watermarking Techniques through Hybrid Methods. Advances in Multimedia. 2020. 1-12. 10.1155/2020/7912690. DOI: https://doi.org/10.1155/2020/7912690
Jay Kumar Jain, & Waoo, A. A. . (2023). An Artificial Neural Network Technique for Prediction of Cyber-Attack using Intrusion Detection System. Journal of Artificial Intelligence, Machine Learning and Neural Network (JAIMLNN) ISSN: 2799-1172, 3(02), 33–42. DOI: https://doi.org/10.55529/jaimlnn.32.33.42
Chauhan, Ms & Waoo, Akhilesh & Patheja, Pushpinder. (2012). INFORMATION HIDING WATERMARKING DETECTION TECHNIQUE BY PSNR AND RGB INTENSITY. 3. 18-22.
Soni, Brijesh & Waoo, Akhilesh. (2023). Deep Learning: Tools and Models. 10.1002/9781119792161.ch3. DOI: https://doi.org/10.1002/9781119792161.ch3
Sharma, Siddhant & Waoo, Akhilesh. (2023). An efficient machine learning technique for prediction of consumer behaviour with high accuracy. International Journal of Computing and Artificial Intelligence. 4. 12-15. 10.33545/27076571.2023.v4.i1a.59. DOI: https://doi.org/10.33545/27076571.2023.v4.i1a.59
Bhatele, K. R., Jha, A., Tiwari, D., Bhatele, M., Sharma, S., Mithora, M. R., & Singhal, S. (2022). COVID-19 Detection: A Systematic Review of Machine and Deep Learning-Based Approaches Utilizing Chest X-Rays and CT Scans. Cognitive Computation, 1–38. Advance online publication. DOI: https://doi.org/10.1007/s12559-022-10076-6
Tomar, R. S., Chaturvedi, P., & Bhatele, M. A Survey on Information Hiding using Water Marking Techniques.
Mishra, M., & Bhatele, M. An Extensive Survey Expounding Security Issues & Requirement in Secure Cloud Computing Environment.
Saganowski, L., Andrysiak, T., Kozik, R., & Choraś, M. (2016). DWT-based anomaly detection method for cyber security of wireless sensor networks. Secur. Commun. Networks, 9, 2911-2922. DOI: https://doi.org/10.1002/sec.1550
Bianca, Tagliaro, Beasley., George, D., O'Mahony., Sergi, Gomez, Quintana., Andriy, Temko., Emanuel, Popovici. (2020). Lightweight Anomaly Detection Framework for IoT. doi: 10.1109/ISSC49989.2020.9180205 DOI: https://doi.org/10.1109/ISSC49989.2020.9180205
Nouar, AlDahoul., Hezerul, Abdul, Karim., Abdulaziz, Saleh, Ba, Wazir. (2021). Model fusion of deep neural networks for anomaly detection. Journal of Big Data, doi: 10.1186/S40537-021-00496-W DOI: https://doi.org/10.1186/s40537-021-00496-w
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Swati Thakur, Mukta Bhatele, Akhilesh A Waoo
This work is licensed under a Creative Commons Attribution 4.0 International License.
With the licence CC-BY, authors retain the copyright, allowing anyone to download, reuse, re-print, modify, distribute, and/or copy their contribution. The work must be properly attributed to its author.
It is not necessary to ask for further permission from the author or journal board.
This journal provides immediate open access to its content on the principle that making research freely available to the public supports a greater global exchange of knowledge.
