Adversarial Attacks on Deep Neural Network: Developing Robust Models Against Evasion Technique

Geeta Sandeep Nadella, Hari Gonaygunta, Karthik Meduri, Snehal Satish

Abstract


In the fast-paced field of machine learning, it is important to build agile models that can correctly classify data in the face of enemy attacks. This paper explores the field of adversarial attacks on deep neural networks (DNNs) and explores ways to increase their flexibility models against theft techniques. Using tensor flow and care packages, we created a DNN model using a well-studied MNIST dataset. The model's architecture consists of sequential layers: dropouts-layers to reduce over-fitting, dense dense-layers through active rule for feature extraction, and a flat layer for preparing input data. Our model performed surprisingly well after careful training and evaluation, with a test accuracy of 97.82%. Notably, this model demonstrates resilience to common malware attacks, highlighting its effectiveness in practical applications. This work complements the growing body of literature on anti-machine learning and highlights how important it is to build robust models to improve security and dependencies in machine learning applications.

Full Text:

PDF

References


Yu, L., Qin, S., Zhang, M., Shen, C., Jiang, T. and Guan, X., 2021. A review of deep reinforcement learning for smart building energy management. IEEE Internet of Things Journal, 8(15), pp.12046-12063.

Daissaoui, A., Boulmakoul, A., Karim, L. and Lbath, A., 2020. IoT and big data analytics for smart buildings: A survey. Procedia computer science, 170, pp.161-168.

Chen, S., Wu, Z. and Christofides, P.D., 2021. Cyber-security of centralized, decentralized, and distributed control-detector architectures for nonlinear processes. Chemical Engineering Research and Design, 165, pp.25-39.

Hu, B., Zhou, C., Tian, Y.C., Hu, X. and Junping, X., 2020. Decentralized consensus decision-making for cybersecurity protection in multimicrogrid systems. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 51(4), pp.2187-2198.

Bonnah, E. and Shiguang, J., 2020. DecChain: A decentralized security approach in Edge Computing based on Blockchain. Future Generation Computer Systems, 113, pp.363-379.

Grechaninov, V., Hulak, H., Hulak, E., Skladannyi, P. and Sokolov, V., 2021. Decentralized Access Demarcation System Construction in Situational Center Network. Cybersecurity Providing in Information and Telecommunication Systems II 2021, 3188(2), pp.197-206.

Bodkhe, U., Mehta, D., Tanwar, S., Bhattacharya, P., Singh, P.K. and Hong, W.C., 2020. A survey on decentralized consensus mechanisms for cyber physical systems. IEEE Access, 8, pp.54371-54401.

Appiah-Kubi, J. and Liu, C.C., 2020. Decentralized intrusion prevention (DIP) against coordinated cyberattacks on distribution automation systems. IEEE Open Access Journal of Power and Energy, 7, pp.389-402.

Agrawal, S., Sarkar, S., Aouedi, O., Yenduri, G., Piamrat, K., Alazab, M., Bhattacharya, S., Maddikunta, P.K.R. and Gadekallu, T.R., 2022. Federated learning for intrusion detection system: Concepts, challenges and future directions. Computer Communications, 195, pp.346-361.

Campos, E.M., Saura, P.F., González-Vidal, A., Hernández-Ramos, J.L., Bernabe, J.B., Baldini, G. and Skarmeta, A., 2022. Evaluating Federated Learning for intrusion detection in Internet of Things: Review and challenges. Computer Networks, 203, p.108661.

Alazab, M., RM, S.P., Parimala, M., Maddikunta, P.K.R., Gadekallu, T.R. and Pham, Q.V., 2021. Federated learning for cybersecurity: Concepts, challenges, and future directions. IEEE Transactions on Industrial Informatics, 18(5), pp.3501-3509.

Mishra, P., Biancolillo, A., Roger, J.M., Marini, F. and Rutledge, D.N., 2020. New data preprocessing trends based on ensemble of multiple preprocessing techniques. TrAC Trends in Analytical Chemistry, 132, p.116045.

Luengo, J., García-Gil, D., Ramírez-Gallego, S., García, S. and Herrera, F., 2020. Big data preprocessing. Cham: Springer.

Fan, C., Chen, M., Wang, X., Wang, J. and Huang, B., 2021. A review on data preprocessing techniques toward efficient and reliable knowledge discovery from building operational data. Frontiers in energy research, 9, p.652801.

Benhar, H., Idri, A. and Fernández-Alemán, J.L., 2020. Data preprocessing for heart disease classification: A systematic literature review. Computer Methods and Programs in Biomedicine, 195, p.105635.

Narkhede, M.V., Bartakke, P.P. and Sutaone, M.S., 2022. A review on weight initialization strategies for neural networks. Artificial intelligence review, 55(1), pp.291-322.

Palanisamy, K., Singhania, D. and Yao, A., 2020. Rethinking CNN models for audio classification. arXiv preprint arXiv:2007.11154.

Huang, X.S., Perez, F., Ba, J. and Volkovs, M., 2020, November. Improving transformer optimization through better initialization. In International Conference on Machine Learning (pp. 4475-4483). PMLR.

A. Mądry, M. Aleksandar, L. Schmidt, & D. Tsipras, "Towards deep learning models resistant to adversarial attacks", 2017. https://doi.org/10.48550/arxiv.1706.06083.

Mammen, P.M., 2021. Federated learning: Opportunities and challenges. arXiv preprint arXiv:2101.05428.

Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W. and Gao, Y., 2021. A survey on federated learning. Knowledge-Based Systems, 216, p.106775.

Li, L., Fan, Y., Tse, M. and Lin, K.Y., 2020. A review of applications in federated learning. Computers & Industrial Engineering, 149, p.106854.

Gafni, T., Shlezinger, N., Cohen, K., Eldar, Y.C. and Poor, H.V., 2022. Federated learning: A signal processing perspective. IEEE Signal Processing Magazine, 39(3), pp.14-41.

Jiang, J.C., Kantarci, B., Oktug, S. and Soyata, T., 2020. Federated learning in smart city sensing: Challenges and opportunities. Sensors, 20(21), p.6230.

Nazah, S., Huda, S., Abawajy, J. and Hassan, M.M., 2020. Evolution of dark web threat analysis and detection: A systematic approach. Ieee Access, 8, pp.171796-171819.

Oz, H., Aris, A., Levi, A. and Uluagac, A.S., 2022. A survey on ransomware: Evolution, taxonomy, and defense solutions. ACM Computing Surveys (CSUR), 54(11s), pp.1-37.

Caviglione, L., Choraś, M., Corona, I., Janicki, A., Mazurczyk, W., Pawlicki, M. and Wasielewska, K., 2020. Tight arms race: Overview of current malware threats and trends in their detection. IEEE Access, 9, pp.5371-5396.

Ramesh, G., Logeshwaran, J. and Aravindarajan, V., 2022. The Performance Evolution of Antivirus Security Systems in Ultra dense Cloud Server Using Intelligent Deep Learning. BOHR International Journal of Computational Intelligence and Communication Network, 1(1), pp.15-19.

Malhotra, P., Singh, Y., Anand, P., Bangotra, D.K., Singh, P.K. and Hong, W.C., 2021. Internet of things: Evolution, concerns and security challenges. Sensors, 21(5), p.1809.

N. Akhtar and A. Mian, "Threat of adversarial attacks on deep learning in computer vision: a survey", IEEE Access, vol. 6, p. 14410-14430, 2018. https://doi.org/10.1109/access.2018.2807385.

Samek, W., Montavon, G., Lapuschkin, S., Anders, C. J., & Müller, K. R. (2021). Explaining deep neural networks and beyond: A review of methods and applications. Proceedings of the IEEE, 109(3), 247-278.

Olu-Ajayi, R., Alaka, H., Sulaimon, I., Sunmola, F., & Ajayi, S. (2022). Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques. Journal of Building Engineering, 45, 103406.

Srinidhi, C. L., Ciga, O., & Martel, A. L. (2021). Deep neural network models for computational histopathology: A survey. Medical image analysis, 67, 101813.


Refbacks

  • There are currently no refbacks.