{"doi":"10.1145/3681780.3697244","publisher":"ACM","editor":[{"full_name":"Omitaomu, Olufemi A.","last_name":"Omitaomu","first_name":"Olufemi A."},{"first_name":"Ali","last_name":"Mostafavi","full_name":"Mostafavi, Ali"},{"full_name":"Randhawa, Sukanya","last_name":"Randhawa","first_name":"Sukanya"},{"first_name":"Haoran","last_name":"Niu","full_name":"Niu, Haoran"}],"author":[{"id":"248865","first_name":"Sanaullah","orcid":"0000-0003-4112-802X","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-4112-802X/work/171159565","last_name":"Sanaullah","full_name":"Sanaullah, Sanaullah"},{"orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-6902-6116/work/171438641","last_name":"Attaullah","full_name":"Attaullah, Hasina","id":"254998","orcid":"0000-0002-6902-6116","first_name":"Hasina"},{"id":"242294","first_name":"Thorsten","orcid":"0000-0001-7425-8766","last_name":"Jungeblut","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0001-7425-8766/work/171159566","full_name":"Jungeblut, Thorsten"}],"date_updated":"2024-11-11T16:31:07Z","page":"50-53","place":"New York, NY, USA","language":[{"iso":"eng"}],"type":"conference","publication_identifier":{"isbn":["9798400711565"]},"conference":{"end_date":"2024-11-01","start_date":"2024-10-29","location":"Atlanta GA USA","name":"SIGSPATIAL '24: The 32nd ACM International Conference on Advances in Geographic Information Systems"},"abstract":[{"text":"In recent years, as urban AI applications increasingly rely on sensitive data, ensuring the privacy and security of machine learning (ML) models has become essential. The proposed research study evaluates the performance and security trade-offs of seven encryption techniques applied to ML models used in urban AI settings. We compare encryption methods, including mixed homomorphic encryptions using Convolutional Neural Networks (CNNs) trained on the MNIST dataset, we analyze how these encryption methods affect model performance in terms of accuracy, error rate, and information leakage. The CNN models, after being trained with encrypted data, are deployed on embedded devices to evaluate real-time performance. We measure key metrics, including execution time, memory usage, and classification accuracy, to assess the feasibility of each encryption method in urban AI scenarios. Additionally, the impact of encryption on model interpretability and robustness is considered, particularly when used in urban applications like intelligent transportation systems, smart city sensors, and surveillance systems. By evaluating error rates, mutual information scores, and statistical properties such as mean and variance, this research aims to explore the practical trade-offs between security, privacy, and performance. Our findings highlight the importance of selecting appropriate encryption techniques for urban AI tasks to maintain both data privacy and model efficiency in real-world settings.","lang":"eng"}],"publication_status":"published","year":"2024","_id":"5098","status":"public","date_created":"2024-11-07T08:52:45Z","publication":"Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI","title":"Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications","user_id":"220548","citation":{"alphadin":"<span style=\"font-variant:small-caps;\">Sanaullah, Sanaullah</span> ; <span style=\"font-variant:small-caps;\">Attaullah, Hasina</span> ; <span style=\"font-variant:small-caps;\">Jungeblut, Thorsten</span>: Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications. In: <span style=\"font-variant:small-caps;\">Omitaomu, O. A.</span> ; <span style=\"font-variant:small-caps;\">Mostafavi, A.</span> ; <span style=\"font-variant:small-caps;\">Randhawa, S.</span> ; <span style=\"font-variant:small-caps;\">Niu, H.</span> (Hrsg.): <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i>. New York, NY, USA : ACM, 2024, S. 50–53","short":"S. Sanaullah, H. Attaullah, T. Jungeblut, in: O.A. Omitaomu, A. Mostafavi, S. Randhawa, H. Niu (Eds.), Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI, ACM, New York, NY, USA, 2024, pp. 50–53.","ieee":"S. Sanaullah, H. Attaullah, and T. Jungeblut, “Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications,” in <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i>, Atlanta GA USA, 2024, pp. 50–53.","chicago":"Sanaullah, Sanaullah, Hasina Attaullah, and Thorsten Jungeblut. “Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications.” In <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i>, edited by Olufemi A. Omitaomu, Ali Mostafavi, Sukanya Randhawa, and Haoran Niu, 50–53. New York, NY, USA: ACM, 2024. <a href=\"https://doi.org/10.1145/3681780.3697244\">https://doi.org/10.1145/3681780.3697244</a>.","apa":"Sanaullah, S., Attaullah, H., &#38; Jungeblut, T. (2024). Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications. In O. A. Omitaomu, A. Mostafavi, S. Randhawa, &#38; H. Niu (Eds.), <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i> (pp. 50–53). New York, NY, USA: ACM. <a href=\"https://doi.org/10.1145/3681780.3697244\">https://doi.org/10.1145/3681780.3697244</a>","mla":"Sanaullah, Sanaullah, et al. “Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications.” <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i>, edited by Olufemi A. Omitaomu et al., ACM, 2024, pp. 50–53, doi:<a href=\"https://doi.org/10.1145/3681780.3697244\">10.1145/3681780.3697244</a>.","ama":"Sanaullah S, Attaullah H, Jungeblut T. Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications. In: Omitaomu OA, Mostafavi A, Randhawa S, Niu H, eds. <i>Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI</i>. New York, NY, USA: ACM; 2024:50-53. doi:<a href=\"https://doi.org/10.1145/3681780.3697244\">10.1145/3681780.3697244</a>","bibtex":"@inproceedings{Sanaullah_Attaullah_Jungeblut_2024, place={New York, NY, USA}, title={Encryption Techniques for Privacy-Preserving CNN Models: Performance and Practicality in Urban AI Applications}, DOI={<a href=\"https://doi.org/10.1145/3681780.3697244\">10.1145/3681780.3697244</a>}, booktitle={Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Advances in Urban-AI}, publisher={ACM}, author={Sanaullah, Sanaullah and Attaullah, Hasina and Jungeblut, Thorsten}, editor={Omitaomu, Olufemi A. and Mostafavi, Ali and Randhawa, Sukanya and Niu, HaoranEditors}, year={2024}, pages={50–53} }"}}