Efficient and Secure GANs: A Survey on Privacy-Preserving and Resource-Aware Models
Source abstract
Abstract
Generative Adversarial Networks (GANs) generate synthetic content to support applications such as data augmentation, image-to-image translation, and training models where data availability is limited. Nevertheless, their broader deployment is constrained by limitations in data availability, high computational and energy demands, as well as privacy and security concerns. These factors restrict their scalability and integration in real-world applications. This survey provides a systematic review of research aimed at addressing these challenges. Techniques such as few-shot learning, consistency regularization, and advanced data augmentation are examined to address data scarcity. Approaches designed to reduce computational and energy costs, including hardware-based acceleration and model optimization, are also considered. In addition, strategies to improve privacy and security, such as privacy-preserving GAN architectures and defense mechanisms against adversarial attacks, are analyzed. By organizing the literature into these thematic categories, the review highlights available solutions, their trade-offs, and remaining open issues. Our findings underline the growing role of GANs in artificial intelligence, while also emphasizing the importance of efficient, sustainable, and secure designs. This work not only concentrates the current knowledge but also sets the basis for future research.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Brain Tumor Detection and Classification · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Informatics and Computer Engineering, School of Engineering, University of West Attica, 11521 Athens, Greece
Department of Electrical and Electronic Engineering Educators, School of Pedagogical and Technological Education (ASPETE), 15122 Athens, Greece
References (100+)
Show source-provided references
1. Deep learning10.1038/nature14539 ↗
2. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press. Available online: https://mitpress.mit.edu/9780262035613/deep-learning/.
3. Generative adversarial networks: An overview10.1109/MSP.2017.2765202 ↗
4. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (2017). Progressive growing of GANs for improved quality, stability, and variation. arXiv.
5. Brock, A., Donahue, J., and Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. arXiv.
6. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv.
7. Karras, T., Laine, S., and Aila, T. (2019, January 15–20). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00453 ↗
8. Yu, L., Zhang, W., Wang, J., and Yu, Y. (2017, January 4–9). SeqGAN: Sequence generative adversarial nets with policy gradient. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.10.1609/aaai.v31i1.10804 ↗
9. Generative adversarial network in medical imaging: A review10.1016/j.media.2019.101552 ↗
10. Eckerli, F., and Osterrieder, J. (2021). Generative adversarial networks in finance: An overview. arXiv.10.2139/ssrn.3864965 ↗
11. Luleci, F., Catbas, F.N., and Avci, O. (2022). A literature review: Generative adversarial networks for civil structural health monitoring. Front. Built Environ., 8.10.3389/fbuil.2022.1027379 ↗
12. Applications of generative adversarial networks (GANs): An updated review10.1007/s11831-019-09388-y ↗
13. Generative adversarial networks (GANs): Challenges, solutions, and future directions10.1145/3446374 ↗
14. Deep Learning Based Carbon Emissions Forecasting and Renewable Energy’s Impact Quantification10.1049/rpg2.12641 ↗
15. Towards the systematic reporting of the energy and carbon footprints of machine learning
16. Strubell, E., Ganesh, A., and McCallum, A. (2020, January 7–12). Energy and policy considerations for deep learning in NLP. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.
17. Green AI10.1145/3381831 ↗
18. Li, T., and Clifton, C. (2021). Differentially private imaging via latent space manipulation. arXiv.
19. Generative adversarial networks: A survey toward private and secure applications10.1145/3459992 ↗
20. Padariya, D., Wagner, I., Taherkhani, A., and Boiten, E. (2025). Privacy-Preserving Generative Models: A Comprehensive Survey. arXiv.
21. Gurumurthy, S., Sarvadevabhatla, R.K., and Babu, R.V. (2017, January 21–26). DeLiGAN: Generative adversarial networks for diverse and limited data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.525 ↗
22. Yadav, P., Sihag, G., and Vijay, V. (2025). Rebalancing the scales: A systematic mapping study of generative adversarial networks (GANs) in addressing data imbalance. arXiv.
23. Lin, Z., Sekar, V., and Fanti, G. (2021, January 13–15). On the privacy properties of GAN-generated samples. Proceedings of the International Conference on Artificial Intelligence and Statistics, Online.
24. Privacy re-identification attacks on tabular GANs10.1002/spy2.469 ↗
25. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
26. Denton, E.L., Chintala, S., and Fergus, R. (2015). Deep Generative Image Models Using a Laplacian Pyramid of Adversarial Networks. arXiv.
27. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6–11). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning (ICML), Sydney, NSW, Australia. Available online: https://proceedings.mlr.press/v70/arjovsky17a.html.
28. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved techniques for training GANs. Advances in Neural Information Processing Systems, American Institute of Physics. Available online: https://proceedings.neurips.cc/paper/2016/hash/8a3363abe792db2d8761d6403605aeb7-Abstract.html.
29. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Advances in Neural Information Processing Systems, American Institute of Physics. Available online: https://proceedings.neurips.cc/paper/2017/hash/8a1d694707eb0fefe65871369074926d-Abstract.html.
30. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
31. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Unpaired image-to-image translation using cycle-consistent adversarial networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.244 ↗
32. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020, January 14–19). Analyzing and improving the image quality of StyleGAN. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00813 ↗
33. Karras, T., Aittala, M., Laine, S., Härkönen, E., Hellsten, J., Lehtinen, J., and Aila, T. (2021). Alias-free generative adversarial networks. arXiv.
34. State Filtered Disturbance Rejection Control10.1007/s11071-024-10449-6 ↗
35. Multilayer Neurocontrol of High-Order Uncertain Nonlinear Systems with Active Disturbance Rejection10.1002/rnc.7118 ↗
36. Shiri, M., Bruno, A., and Loiacono, D. (2024, January 2–5). Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs. Proceedings of the International Conference on Pattern Recognition (ICPR), Kolkata, India.10.1007/978-3-031-87660-8_14 ↗
37. Generative adversarial networks (GANs) for image augmentation in farming: A review10.1109/ACCESS.2024.3505989 ↗
38. Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review10.1016/j.compag.2022.107208 ↗
39. Donahue, C., McAuley, J., and Puckette, M. (2018). Adversarial audio synthesis. arXiv.
40. Fahimi, F., Zhang, Z., Goh, W.B., Ang, K.K., and Guan, C. (2019, January 19–22). Towards EEG generation using GANs for BCI applications. Proceedings of the IEEE EMBS International Conference on Biomedical & Health Informatics, Chicago, IL, USA.10.1109/BHI.2019.8834503 ↗
41. Amin, S.S., and Ragha, L. (2020, January 15–16). Alphanumeric character recognition on tiny dataset. Proceedings of the International Conference on Computer Networks, Big data and IoT (ICCBI), Madurai, India.10.1007/978-3-030-43192-1_73 ↗
42. Iyer, S., and Hou, T.T. (2023). GAT-GAN: A graph-attention-based time-series generative adversarial network. arXiv.
43. Yoon, J., Jarrett, D., and Van der Schaar, M. (2019). Time-series generative adversarial networks. Advances in Neural Information Processing Systems, American Institute of Physics. Available online: https://papers.nips.cc/paper/8789-time-series-generative-adversarial-networks.pdf.
44. Wang, J., Ju, B., Qian, X., Ye, M., and Huo, W. (2024, January 12–15). Graph-based generative adversarial networks for molecular generation with noise diffusion. Proceedings of the 14th International Conference on Bioscience, Biochemistry and Bioinformatics, Kyoto, Japan.10.1145/3640900.3640911 ↗
45. Choi, J., Lee, J., Yoon, C., Park, J.H., Hwang, G., and Kang, M. (2021). Do not escape from the manifold: Discovering the local coordinates on the latent space of GANs. arXiv.
46. Bhagoji, A.N., He, W., Li, B., and Song, D. (2017). Exploring the space of black-box attacks on deep neural networks. arXiv.
47. Farkaš, I. (2021). On mode collapse in generative adversarial networks. Artificial Neural Networks and Machine Learning—ICANN 2021, Proceedings of the International Conference on Artificial Neural Networks, Online, 14–17 September 2021, Springer.10.1007/978-3-030-86365-4 ↗
48. Figueira, A., and Vaz, B. (2022). Survey on synthetic data generation, evaluation methods and GANs. Mathematics, 10.10.3390/math10152733 ↗
49. Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., and Aila, T. (2020). Training generative adversarial networks with limited data. arXiv.
50. Generalizing from a few examples: A survey on few-shot learning10.1145/3386252 ↗
51. Tanaka, F.H.K., and Aranha, C. (2019). Data augmentation using GANs. arXiv.
52. Zhao, M., Cong, Y., and Carin, L. (2020, January 12–18). On leveraging pretrained GANs for generation with limited data. Proceedings of the International Conference on Machine Learning, Vienna, Austria. Available online: https://proceedings.mlr.press/v119/zhao20a.html.
53. Bai, C.-Y., Lin, H.-T., Raffel, C., and Kan, W.C.-W. (2021, January 14–18). On Training Sample Memorization: Lessons from Benchmarking Generative Modeling with a Large-scale Competition. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Online.10.1145/3447548.3467198 ↗
54. Feng, Q., Guo, C., Benitez-Quiroz, F., and Martinez, A.M. (2021, January 11–17). When do GANs replicate? On the choice of dataset size. Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, BC, Canada.10.1109/ICCV48922.2021.00663 ↗
55. Semi-supervised few-shot learning approach for plant diseases recognition10.1186/s13007-021-00770-1 ↗
56. Middel, L., Palm, C., and Erdt, M. (2019). Synthesis of medical images using GANs. Uncertainty for Safe Utilization of Machine Learning in Medical Imaging and Clinical Image-Based Procedures, Proceedings of the First International Workshop, UNSURE 2019, and 8th International Workshop, CLIP 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, 17 October 2019, Springer International Publishing.10.1007/978-3-030-32689-0_13 ↗
57. Low-resource language discrimination toward Chinese dialects with transfer learning and data augmentation10.1145/3473499 ↗
58. A generative adversarial network for data augmentation: The case of Arabic regional dialects10.1016/j.procs.2021.05.072 ↗
59. Chen, Z., Ramachandra, B., and Vatsavai, R.R. (2020). Consistency regularization with generative adversarial networks for semi-supervised learning. arXiv.
60. Zhao, Z., Singh, S., Lee, H., Zhang, Z., Odena, A., and Zhang, H. (2021, January 2–9). Improved consistency regularization for GANs. Proceedings of the AAAI Conference on Artificial Intelligence, Online.10.1609/aaai.v35i12.17317 ↗
61. Zhang, H., Zhang, Z., Odena, A., and Lee, H. (2019). Consistency regularization for generative adversarial networks. arXiv.
62. A Systematic Review on Data Scarcity Problem in Deep Learning: Solution and Applications10.1145/3502287 ↗
63. The Future of Artificial Intelligence in the Face of Data Scarcity
64. Narayanan, H., and Ghanta, S. (2024). A Study of Data Augmentation Techniques to Overcome Data Scarcity in Wound Classification Using Deep Learning. arXiv.
65. A Systematic Survey of Regularization and Normalization in GANs10.1145/3569928 ↗
66. Advancements in Data Augmentation and Transfer Learning: A Comprehensive Survey to Address Data Scarcity Challenges10.2174/0126662558286875231215054324 ↗
67. An Energy-Efficient GAN Accelerator with On-Chip Training for Domain-Specific Optimization10.1109/JSSC.2021.3094469 ↗
68. Bhattacharya, G. (2021). From DNNs to GANs: Review of Efficient Hardware Architectures for Deep Learning. arXiv.
69. Douwes, C., Esling, P., and Briot, J.-P. (2021). Energy consumption of deep generative audio models. arXiv.
70. PRIME: A novel processing-in-memory architecture for neural network computation in ReRAM-based main memory10.1145/3007787.3001140 ↗
71. Liu, F., Liu, C., and Bi, F. (2018). A memristor based unsupervised neuromorphic system towards fast and energy-efficient GAN. arXiv.
72. Li, M., Lin, J., Ding, Y., Liu, Z., Zhu, J.Y., and Han, S. (2020, January 14–19). GAN compression: Efficient architectures for interactive conditional GANs. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.00533 ↗
73. A survey on GAN acceleration using memory compression techniques10.1186/s44147-021-00045-5 ↗
74. Polizzi, Z., and Tsai, C.-Y. (2020). FusedProp: Towards efficient training of generative adversarial networks. arXiv.
75. Satyam, S., Nikam, H., and Sahay, S. (2021). Energy-efficient implementation of generative adversarial networks on passive RRAM crossbar arrays. arXiv.
76. Corda, S., Veenboer, B., and Tolley, E. (2022, January 13–18). PMT: Power measurement toolkit. Proceedings of the 2022 IEEE/ACM International Workshop on HPC User Support Tools (HUST), Dallas, TX, USA.10.1109/HUST56722.2022.00011 ↗
77. Lacoste, A., Luccioni, A., Schmidt, V., and Dandres, T. (2019). Quantifying the carbon emissions of machine learning. arXiv.
78. The growing energy footprint of artificial intelligence10.1016/j.joule.2023.09.004 ↗
79. The carbon footprint of machine learning training will plateau, then shrink10.1109/MC.2022.3148714 ↗
80. Jayakodi, N.K., Doppa, J.R., and Pande, P.P. (2020, January 2–5). SETGAN: Scale and energy trade-off GANs for image applications on mobile platforms. Proceedings of the 2020 IEEE/ACM International Conference on Computer-Aided Design (ICCAD), San Diego, CA, USA.10.1145/3400302.3415675 ↗
81. Kumar, A., Anand, K., Mandloi, S., Mishra, A., Thakur, A., Kasera, N., and AP, P. (2023, January 2–3). CoroNetGAN: Controlled pruning of GANs via hypernetworks. Proceedings of the IEEE/CVF International Conference on Computer Vision, Paris, France.10.1109/ICCVW60793.2023.00136 ↗
82. Zhou, J., Chen, Z., Li, J., Gu, Z., and Liang, Z. (2021). Property inference attacks against GANs. arXiv.10.14722/ndss.2022.23019 ↗
83. Membership Inference Attacks on Machine Learning: A Survey10.1145/3523273 ↗
84. Detection of membership inference attacks on GAN models
85. Shafik, W. (2025). Generative adversarial networks: Security, privacy, and ethical considerations. Generative Artificial Intelligence (AI) Approaches for Industrial Applications, Springer.10.1007/978-3-031-76710-4_5 ↗
86. Liu, Y., Acharya, U.R., and Tan, J.H. (2025). Preserving Privacy in Healthcare: A Systematic Review of Deep Learning Approaches for Synthetic Data Generation. Comput. Methods Programs Biomed., 260.10.1016/j.cmpb.2024.108571 ↗
87. Fredrikson, M., Jha, S., and Ristenpart, T. (2015, January 12–16). Model inversion attacks that exploit confidence information and basic countermeasures. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, Denver, CO, USA.10.1145/2810103.2813677 ↗
88. Deep learning model inversion attacks and defenses: A comprehensive survey10.1007/s10462-025-11248-0 ↗
89. GAN you see me? Enhanced data reconstruction attacks against split inference
90. Shieh, C.-S., Nguyen, T.-T., Lin, W.-W., Huang, Y.-L., Horng, M.-F., Lee, T.-F., and Miu, D. (2022). Detection of adversarial DDoS attacks using generative adversarial networks with dual discriminators. Symmetry, 14.10.3390/sym14010066 ↗
91. A Comprehensive Survey of Generative Adversarial Networks (GANs) in Cybersecurity Intrusion Detection10.1109/ACCESS.2023.3296707 ↗
92. Cui, F., Ye, Q., and Kibenge-MacLeod, P. (June, January 28). A Wasserstein GAN-based framework for adversarial attacks against intrusion detection systems. Proceedings of the ICC 2023-IEEE International Conference on Communications, Rome, Italy.10.1109/ICC45041.2023.10279233 ↗
93. GANobfuscator: Mitigating Information Leakage Under GAN via Differential Privacy10.1109/TIFS.2019.2897874 ↗
94. Hu, R., Li, X., Zhang, Y., Chen, W., and Wang, L. (2023, January 17–20). CB-GAN: Generate Sensitive Data with a Convolutional Bidirectional Generative Adversarial Networks. Proceedings of the International Conference on Database Systems for Advanced Applications (DASFAA), Tianjin, China.10.1007/978-3-031-30678-5_13 ↗
95. PRISMA (2025, October 05). Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) Statement. Available online: https://www.prisma-statement.org/.
96. Lessons from applying the systematic literature review process within the software engineering domain10.1016/j.jss.2006.07.009 ↗
97. Tseng, H.Y., Jiang, L., Liu, C., Yang, M.H., and Yang, W. (2021, January 19–25). Regularizing generative adversarial networks under limited data. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Online.10.1109/CVPR46437.2021.00783 ↗
98. Tsalera, E., Papadakis, A., Pagiatakis, G., and Samarakou, M. (2025). Impact evaluation of sound dataset augmentation and synthetic generation upon classification accuracy. J. Sens. Actuator Netw., 14.10.3390/jsan14050091 ↗
99. Zhang, Z., Hua, Y., Sun, G., Wang, H., and McLoone, S. (2024, January 2–7). Improving the Leaking of Augmentations in Data-Efficient GANs via Adaptive Negative Data Augmentation. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA.10.1109/WACV57701.2024.00533 ↗
100. Abdollahzadeh, A., Xiao, Y., Wang, Y., Huang, T., Patel, V.M., and Metaxas, D. (2023). A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot. arXiv.