Secure Reversible Transformations through Neural Coupling Architecture

References

[1] C. E. Shannon, “Communication Theory of Secrecy Systems,” Bell System Technical Journal, vol. 28, no. 4, pp. 656–715, 1949.

[2] A. J. Menezes, P. C. van Oorschot, and S. A. Vanstone, Handbook of Applied Cryptography, CRC Press, 1996.

[3] M. Abadi and D. G. Andersen, “Learning to Protect Communications with Adversarial Neural Cryptography,” in Proc. International Conference on Learning Representations (ICLR), 2017.

[4] I. Goodfellow et al., “Generative Adversarial Nets,” in Advances in Neural Information Processing Systems (NeurIPS), 2014.

[5] L. Dinh, J. Sohl-Dickstein, and S. Bengio, “Density Estimation using Real NVP,” in Proc. International Conference on Learning Representations (ICLR), 2017.

[6] D. P. Kingma and P. Dhariwal, “Glow: Generative Flow with Invertible 1×1 Convolutions,” in Advances in Neural Information Processing Systems (NeurIPS), 2018.

[7] D.J. Rezende and S. Mohamed, “Variational Inference with Normalizing Flows,” in International Conference on Machine Learning (ICML), 2015.

[8] G. Papamakarios, E. Nalisnick, D. J. Rezende, S. Mohamed, and B. Lakshminarayanan, “Normalizing Flows for Probabilistic Modeling and Inference,” Journal of Machine Learning Research, vol. 22, pp. 1–64, 2021.

[9] A. Kerckhoffs, “La cryptographie militaire,” Journal des sciences militaires, vol. 9, pp. 5–83, 1883.

[10] A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” in Advances in Neural Information Processing Systems (NeurIPS), 2019.

[11] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in Proc. International Conference on Learning Representations (ICLR), 2015.

[12] C. M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.

[13] T. M. Cover and J. A. Thomas, Elements of Information Theory, Wiley, 2006.

[14] I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, “Improved Training of Wasserstein GANs,” in Advances in Neural Information Process ing Systems (NeurIPS), 2017.

[15] R. Pascanu, T. Mikolov, and Y. Bengio, “On the difficulty of training recurrent neural networks,” in International Conference on Machine Learning (ICML), 2013.

[16] J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer Normalization,” arXiv preprint 690 arXiv:1607.06450, 2016.

[17] J. Daemen and V. Rijmen, The Design of Rijndael: AES– The Advanced Encryption Standard, Springer, 2002.

[18] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, pp. 1929–1958, 2014.

[19] D. Grangier and M. A. Brunner, “Neural Stream Ciphers: Continuous Representations for Learned Encryption,” in Advances in Neural Information Processing Systems (NeurIPS), 2019.

[20] J. Bonneau, C. Herley, P. C. van Oorschot, and F. Stajano, “Passwords and the 700 Evolution of Imperfect Authentication,” Communications of the ACM, vol. 58, no. 7, pp. 78–87, 2015.

[21] K. He, X. Zhang, S. Ren, and J. Sun, “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015.

@article{1715290,
      author = {Kunal Sood, Raunak Singh, Girish Mishra},
      title = {Secure Reversible Transformations through Neural Coupling Architecture},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {9},
      pages = {1621-1633},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1715290.pdf},
      abstract = {This work presents a neural-based cryptographic framework that integrates properties of both block ciphers and stream ciphers through an invertible coupling network. The model employs afixed-key, 128-bit transformation in which encryption and decryption are learned jointly, while an adversarial network attempts unauthorized plaintext recovery. Using Real-NVP-style affine coupling layers, the system ensures exact invertibility and secure reversible transformations. Adversarial training enables near-perfect reconstruction for the legitimate receiver while maintaining high uncertainty for the adversary. By combining fixed transformations with continuous ciphertext outputs and noise-based perturbations, the framework exhibits dual characteristics of classical block and stream ciphers. Experimental results demonstrate the effectiveness of the approach as a hybrid neural cryptographic mechanism, providing secure, learnable encryption without hand-designed structures.},
      keywords = {Adversarial Learning, Hybrid Block–Stream Cipher, Invertible Neural Networks, Key-Conditioned Encryption, Neural Cryptography},
      month = {March},
      doi = {https://doi.org/10.64388/IREV9I9-1715290}
  }