High-capacity image steganography secured by universal adversarial perturbations
Arun Kumar Singhaksingh1@ggn.amity.eduDepartment of Electronics and Communication EngineeringAmity University HaryanaGurugram, Haryana, 122413, IndiaView full profile → , *Juhi SinghCorresponding authorjuhi.singh@jaipur.manipal.eduDepartment of Computer Science and EngineeringManipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 05 Nov 2024
- Published Online:
- 30 Aug 2025
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-2462
- Pages:
- 2227–2235
Abstract
Keywords
Subject Classifications
References
[1] M. Alanzy, R. Alomrani, B. Alqarni, and S. Almutairi, “Image steganography using LSB and hybrid encryption algorithms,” Applied Sciences, vol. 13, no. 21, p. 11771 (2023). [Online]. Available: https://doi.org/10.3390/app132111771
[2] A. K. Singh, J. Singh, and H. V. Singh, “Steganography in images using LSB technique,” International Journal of Latest Trends in Engineering and Technology (IJLTET), vol. 5, no. 1, pp. 426–430 (Jan. 2015).
[3] A. Nguyen, J. Yosinski, and J. Clune, “Deep neural networks are easily fooled: High confidence predictions for unrecognizable images,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 427–436 (2015).
[4] W. Tang, “CNN-based adversarial embedding for image steganography,” IEEE Trans. Inf. Forensics Security, vol. 14, no. 8, pp. 2074–2087 (2019), doi: 10.1109/TIFS.2019.2891237.
[5] A. Kurakin, I. J. Goodfellow, and S. Bengio, “Adversarial examples in the physical world,” in Artificial Intelligence Safety and Security, R. V. Yampolskiy, Ed. Boca Raton, FL, USA: Chapman and Hall/CRC, pp. 99–112 (2018).
[6] A. Su and X. Zhao, “Boosting image steganalysis under universal deep learning architecture incorporating ensemble classification strategy,” IEEE Signal Process. Lett., vol. 26, no. 12, pp. 1852–1856 (Dec. 2019), doi: 10.1109/LSP.2019.2950081.
[7] J. Ye, J. Ni, and Y. Yi, “Deep learning hierarchical representations for image steganalysis,” IEEE Trans. Inf. Forensics Security, vol. 12, no. 11, pp. 2545–2557 (Nov. 2017), doi: 10.1109/TIFS.2017.2710946.
[8] B. Li, W. Wei, A. Ferreira, and S. Tan, “ReST-Net: Diverse activation modules and parallel subnets-based CNN for spatial image steganalysis,” IEEE Signal Process. Lett., vol. 25, no. 5, pp. 650–654 (May 2018), doi: 10.1109/LSP.2018.2816569.
[9] G. Xu, H.-Z. Wu, and Y.-Q. Shi, “Structural design of convolutional neural networks for steganalysis,” IEEE Signal Process. Lett., vol. 23, no. 5, pp. 708–712 (May 2016), doi: 10.1109/LSP.2016.2548421.
[10] P. Tabacof and E. Valle, “Exploring the space of adversarial images,” in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Vancouver, Canada, pp. 426–433 (2016), doi: 10.1109/IJCNN.2016.7727230.
[11] S.-M. Moosavi-Dezfooli, A. Fawzi, and P. Frossard, “DeepFool: A simple and accurate method to fool deep neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (2016). doi: 10.48550/arXiv.1511.04599.
[12] S.-M. Moosavi-Dezfooli, A. Fawzi, O. Fawzi, and P. Frossard, “Universal adversarial perturbations,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR) (2017). doi: 10.48550/arXiv.1610.08401.
[13] B. Li, Z. Li, S. Zhou, S. Tan, and X. Zhang, “New steganalytic features for spatial image steganography based on derivative filters and threshold LBP operator,” IEEE Trans. Inf. Forensics Security, vol. 13, no. 5, pp. 1242–1257 (May 2018).
[14] S. Huang, N. Papernot, and I. Goodfellow, “Adversarial attacks on neural network policies,” arXiv preprint, arXiv:1702.02284 (2017).
[15] A. G. Devi, A. Thota, G. Nithya, S. Majji, A. Gopatoti, and L. Dhavamani, “Advancement of digital image steganography using deep convolutional neural networks,” in Proc. 2022 Int. Interdisciplinary Humanitarian Conf. for Sustainability (IIHC), Bengaluru, India, pp. 250–254 (2022), doi: 10.1109/IIHC55949.2022.10060230.
[16] G. S. B. and A. Danti, “Image steganography using discrete wavelet transform and convolutional neural network,” in Proc. 2022 Int. Interdisciplinary Humanitarian Conf. for Sustainability (IIHC), Bengaluru, India, pp. 862–868 (2022), doi: 10.1109/IIHC55949.2022.10060110.
[17] S. Lahiri and P. Paul, “Image steganography on coloured images using edge-based data hiding in DCT domain,” in Proc. IEEE 7th Annu. Inf. Technol., Electron. and Mobile Commun. Conf. (IEMCON), Vancouver, Canada, pp. 1–8 (2016), doi: 10.1109/IEMCON.2016.7746270.
[18] S. A. Kumar, J. Singh, and S. H. Vikram, “DCT- and DWT-based intellectual property right protection in digital images,” Proc. Int. Conf. Artif. Intell. Cogn. Comput., vol. 815, pp. 531–540, Springer (2019). doi: 10.1007/978-981-13-1580-0_49.
[19] S. U. Din, “Steganographic universal adversarial perturbations,” Pattern Recogn. Lett., vol. 135, pp. 146–152 (2020), doi: 10.1016/j.patrec.2020.04.025.
[20] J. Singh and A. K. Singh, “Enhancing digital information concealment through DWT-based coefficient alteration and steganographic technique,” Journal of Discrete Mathematical Sciences & Cryptography, vol. 27, no. 2-A, pp. 283–292 (2024).
[21] B. Lakshmi Sirisha and B. Chandra Mohan, “Review on spatial domain image steganography techniques,” Journal of Discrete Mathematical Sciences & Cryptography, vol. 24, no. 6, pp. 1873–1883 (Sep. 2021).
