1. Jasper Gnana Chandran, J., Karthick, R., Rajagopal, R., & Meenalochini, P. (2023). Dual-channel capsule generative adversarial network optimized with golden eagle optimization for pediatric bone age assessment from hand X-ray image. International Journal of Pattern Recognition and Artificial Intelligence, 37(02), 2354001.
2. Karthick, R., Prabha, M., Sabapathy, S. R., Jiju, D., & Selvan, R. S. (2023, October). Inspired by social-spider behavior for microwave filter optimization, swarm optimization algorithm. In 2023 International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS) (Vol. 1, pp. 1-4). IEEE.
3. Vijayalakshmi, S., Sivaraman, P. R., Karthick, R., & Ali, A. N. (2020, September). Implementation of a new Bi-Directional Switch multilevel Inverter for the reduction of harmonics. In IOP Conference Series: Materials Science and Engineering (Vol. 937, No. 1, p. 012026). IOP Publishing.
4. Kiruthiga, B., Karthick, R., Manju, I., & Kondreddi, K. (2024). Optimizing harmonic mitigation for smooth integration of renewable energy: A novel approach using atomic orbital search and feedback artificial tree control. Protection and Control of Modern Power Systems, 9(4), 160-176.
5. Sulthan Alikhan, J., Miruna Joe Amali, S., & Karthick, R. (2024). Deep Siamese domain adaptation convolutional neural network-based quaternion fractional order Meixner moments fostered big data analytical method for enhancing cloud data security. Network: Computation in Neural Systems, 1-28.
6. Sakthi, P., Bhavani, R., Arulselvam, D., Karthick, R., Selvakumar, S., & Sudhakar, M. (2022, September). Energy efficient cluster head selection and routing protocol for WSN. In AIP Conference Proceedings (Vol. 2518, No. 1). AIP Publishing.
7. Aravindaguru, I., Arulselvam, D., Kanagavalli, N., Ramkumar, V., & Karthick, R. (2022, September). Space cloud in cubesat-Consigning expert system to space. In AIP Conference Proceedings (Vol. 2518, No. 1). AIP Publishing.
8. Karthick, R., Prabaharan, A. M., & Selvaprasanth, P. (2019). A Dumb-Bell shaped damper with magnetic absorber using ferrofluids. International Journal of Recent Technology and Engineering (IJRTE), 8.
9. Selvan, R. S., Wahidabanu, R. S. D., Karthick, B., Sriram, M., & Karthick, R. (2020). Development of Secure Transport System Using VANET. TEM (H-Index), 82.
10. Karthick, R., & Sundararajan, M. (2018). Optimization of MIMO Channels Using an Adaptive LPC Method. International Journal of Pure and Applied Mathematics, 118(10), 131-135.
11. Lopez, S., Sarada, V., Praveen, R. V. S., Pandey, A., Khuntia, M., & Haralayya, D. B. (2024). Artificial intelligence challenges and role for sustainable education in india: Problems and prospects. Sandeep Lopez, Vani Sarada, RVS Praveen, Anita Pandey, Monalisa Khuntia, Bhadrappa Haralayya (2024) Artificial Intelligence Challenges and Role for Sustainable Education in India: Problems and Prospects. Library Progress International, 44(3), 18261-18271.
12. Kumar, N., Kurkute, S. L., Kalpana, V., Karuppannan, A., Praveen, R. V. S., & Mishra, S. (2024, August). Modelling and Evaluation of Li-ion Battery Performance Based on the Electric Vehicle Tiled Tests using Kalman Filter-GBDT Approach. In 2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) (pp. 1-6). IEEE.
13. Sharma, S., Vij, S., Praveen, R. V. S., Srinivasan, S., Yadav, D. K., & VS, R. K. (2024, October). Stress Prediction in Higher Education Students Using Psychometric Assessments and AOA-CNN-XGBoost Models. In 2024 4th International Conference on Sustainable Expert Systems (ICSES) (pp. 1631-1636). IEEE.
14. Yamuna, V., Praveen, R. V. S., Sathya, R., Dhivva, M., Lidiya, R., & Sowmiya, P. (2024, October). Integrating AI for Improved Brain Tumor Detection and Classification. In 2024 4th International Conference on Sustainable Expert Systems (ICSES) (pp. 1603-1609). IEEE.
15. Anuprathibha, T., Praveen, R. V. S., Jayanth, H., Sukumar, P., Suganthi, G., & Ravichandran, T. (2024, October). Enhancing Fake Review Detection: A Hierarchical Graph Attention Network Approach Using Text and Ratings. In 2024 Global Conference on Communications and Information Technologies (GCCIT) (pp. 1-5). IEEE.
Page No: 210 - 215
Abstract : Generative Adversarial Networks (GANs) have demonstrated significant potential in generating synthetic data for various applications, including those involving sensitive information like healthcare and finance. However, two major issues arise when GANs are applied to sensitive datasets: (i) the model may memorize training samples, compromising the privacy of individuals, especially when the data includes personally identifiable information (PII), and (ii) there is a lack of control over the specificity of the generated samples, which limits their utility for tailored use-cases. To address these challenges, we propose a novel framework that integrates differential privacy with latent representation learning to ensure privacy while providing control over the specificity of generated data. Our approach ensures that the synthetic data does not reveal individual data points, and by learning effective latent codes, it allows for the generation of specific and meaningful data. We evaluate our method using the MNIST dataset, showing that it preserves privacy and demonstrates a privacy-utility trade-off, where increased privacy leads to decreased classification accuracy. Additionally, we highlight the computational challenges, as the training process incurs a tenfold increase in time compared to standard GAN models. Finally, we extend our approach to the CelebA dataset, demonstrating how privacy and specificity can be controlled to generate high-quality, private synthetic data.
Keyword Generative Adversarial Networks (GANs), Privacy-preserving learning, Differential privacy, Synthetic data generation, Latent representation learning, Privacy-utility trade-off, differentially private models, Synthetic data for sensitive application, Data specificity control.
Reference: