Kyushu University · Computer Science
Professor Ishak Meraouche's research lab specializes in artificial intelligence-based cryptography, focusing on leveraging deep learning and generative adversarial networks (GANs) to design neural network architectures that can learn secure encryption and decryption protocols. The lab explores adversarial training frameworks to achieve provably secure communication, particularly in multi-party settings, and investigates the theoretical foundations of neural cryptography, including the ability to emulate perfect secrecy like the One-Time Pad. A key direction involves enabling remote synchronization among multiple neural networks to establish secure, dynamic communication channels without traditional key exchange mechanisms.
Figures are computed from collected data and may differ slightly.
A current trend of research focuses on artificial intelligence based cryptography which although proposed almost thirty years ago could not attract much attention. Abadi and Anderson’s work on adversarial cryptography in 2016 rejuvenated the research area which now focuses in building neural networks that are able to learn cryptography using the idea from Generative Adversarial Networks (GANs). In this paper, we survey the most prominent research works that cover neural networks based cryptograp
Neural networks based cryptography has seen a significant growth since the introduction of adversarial cryptography which makes use of Generative Adversarial Networks (GANs) to build neural networks that can learn encryption. The encryption has been proven weak at first but many follow up works have shown that the neural networks can be made to learn the One Time Pad (OTP) and produce perfectly secure ciphertexts. To the best of our knowledge, existing works only considered communications betwee
Open papers in the app to read, cite, and organize with AI.
