Robustness and Security in AI Systems: Defending Against Adversarial Attacks and Malicious Manipulation
Article Sidebar
Main Article Content
Abstract
The increasing deployment of artificial intelligence (AI) systems across various domains has raised concerns about their vulnerability to adversarial attacks and malicious manipulation. the challenges posed by adversarial attacks and malicious manipulation in AI systems and discusses strategies for enhancing their robustness and security. Adversarial attacks, which involve subtly perturbing input data to deceive AI models, can lead to erroneous predictions and compromise the integrity of AI systems. Additionally, malicious actors may exploit vulnerabilities in AI systems to manipulate outcomes for nefarious purposes, such as spreading misinformation or undermining trust in automated decision-making processes. To address these challenges, researchers and practitioners have proposed a variety of techniques for defending against adversarial attacks and enhancing the security of AI systems. These techniques include adversarial training, which involves augmenting training data with adversarial examples to improve model robustness, as well as techniques for model verification and robustness certification.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
You are permitted to share and adapt the material under the terms of Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This means you can distribute and modify the work, provided appropriate credit is given, a link to the license is provided, and it's made clear if any changes were made. However, commercial use of the material is not allowed, meaning you may not use it for commercial purposes without prior permission from the copyright holder.
References
Arth Dave, Lohith Paripati, Venudhar Rao Hajari, Narendra Narukulla, & Akshay Agarwal. (2024). Future Trends: The Impact of AI and ML on Regulatory Compliance Training Programs. Universal Research Reports, 11(2), 93–101. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1257
Bhowmick D, Islam T, Jogesh KS (2019) Assessment of Reservoir Performance of a Well in South-Eastern Part of Bangladesh Using Type Curve Analysis. Oil Gas Res 4: 159. DOI: 10.4172/2472-0518.1000159
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., & Giacinto, G. "Evasion attacks against machine learning at test time." Joint European conference on machine learning and knowledge discovery in databases. Springer, Berlin, Heidelberg (2013).
Biggio, B., & Roli, F. "Wild patterns: Ten years after the rise of adversarial machine learning." Pattern Recognition, 84, 317-331 (2018).
Carlini, N., & Wagner, D. "Towards evaluating the robustness of neural networks." 2017 IEEE Symposium on Security and Privacy (SP). IEEE (2017).
Choudhury, L. K. (2022). STUDY ON ROLE OF LOGIC IN AI18 AND PROBLEM SOLVING USING ARTIFICIAL INTELLIGENCE. Universal Research Reports, 9(4), 282–290. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1042
Dave, A., Banerjee, N., & Patel, C. (2023). FVCARE:Formal Verification of Security Primitives in Resilient Embedded SoCs (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2304.11489
Dr Manoj Kumar Srivastava. (2024). An Analysis of Ownership Rights in AI-Generated Images from an Indian Perspective. Universal Research Reports, 10(4), 226–229. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1196
Dr. Rakesh Kumar. (2018). How AI Contributes to Tailored Online Product Suggestions. Universal Research Reports, 5(1), 674–677. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1236
Goodfellow, I. J., Shlens, J., & Szegedy, C. "Explaining and harnessing adversarial examples." arXiv preprint arXiv:1412.6572 (2014).
Huang, R., Xiao, C., Zhang, B., & Kesidis, G. "Adversarial machine learning." Proceedings of the IEEE, 105(4), 680-699 (2017).
Katragadda, V. . (2024). Leveraging Intent Detection and Generative AI for Enhanced Customer Support. Journal of Artificial Intelligence General Science (JAIGS) ISSN:3006-4023, 5(1), 109–114. https://doi.org/10.60087/jaigs.v5i1.178
Khan, A., & Khan, J. (2023). A Critical Review of Machine Learning of Energy Materials for POC (Particle in cell codes). Universal Research Reports, 10(1), 11–17. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1056
Kumar, D. R. (2021). Information Overload and the Decision-Making Process of Consumers in Today’s World. Innovative Research Thoughts, 7(1), 25–28. Retrieved from https://irt.shodhsagar.com/index.php/j/article/view/1004
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. "Towards deep learning models resistant to adversarial attacks." arXiv preprint arXiv:1706.06083 (2017).
Mandeep, & Dr. Renu Kansal. (2023). Impact of Artificial Intelligence on Training of Autistic Children. Universal Research Reports, 10(4), 281–286. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/1246
Papernot, N., McDaniel, P., Sinha, A., & Wellman, M. "Towards the Science of Security and Privacy in Machine Learning." arXiv preprint arXiv:2008.08231 (2020).
Papernot, N., & McDaniel, P. "Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning." arXiv preprint arXiv:1803.04765 (2018).
Taneja, A. K. (2017). Study of theory of Connectionism and its Components/ stages in the process of learning. Universal Research Reports, 4(2), 53–58. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/91
Thakur, N., Hiwrale, A., & Selote, S. (2017). Artificially Intelligent Chatbot. Universal Research Reports, 4(6), 43–47. Retrieved from https://urr.shodhsagar.com/index.php/j/article/view/187
Tramer, F., Kurakin, A., Papernot, N., Boneh, D., & McDaniel, P. "Ensemble adversarial training: Attacks and defenses." arXiv preprint arXiv:1705.07204 (2017).
Kanungo, S. (2024). Computer aided device for Managing, Monitoring, and Migrating Data Flows in the Cloud (Patent No. 6356178). GB Patent & Intellectual Property Office. https://www.registered-design.service.gov.uk/find/6356178
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. "Intriguing properties of neural networks." arXiv preprint arXiv:1312.6199 (2013).