Unnikrishnan Menon

Anirudh Rajiv Menon, Unnikrishnan Menon, Kailash Ahirwar

Modern deep learning models, growing larger and more complex, have demonstrated exceptional generalization and accuracy due to training on huge datasets. This trend is expected to continue. However, the increasing size of these models poses challenges in training, as traditional centralized methods are limited by memory constraints at such scales. This paper proposes an asynchronous decentralized training paradigm for large modern deep learning models that harnesses the compute power of regular heterogeneous PCs with limited resources connected across the internet to achieve favourable performance metrics. Ravnest facilitates decentralized training by efficiently organizing compute nodes into clusters with similar data transfer rates and compute capabilities, without necessitating that each node hosts the entire model. These clusters engage in $\textit{Zero-Bubble Asynchronous Model Parallel}$ training, and a $\textit{Parallel Multi-Ring All-Reduce}$ method is employed to effectively execute global parameter averaging across all clusters. We have framed our asynchronous SGD loss function as a block structured optimization problem with delayed updates and derived an optimal convergence rate of $O\left(\frac{1}{\sqrt{K}}\right)$. We further discuss linear speedup with respect to the number of participating clusters and the bound on the staleness parameter.

Unnikrishnan Menon, Anirudh Rajiv Menon, Atharva Hudlikar

With meteoric developments in communication systems and data storage technologies, the need for secure data transmission is more crucial than ever. The level of security provided by any cryptosystem relies on the sensitivity of the private key, size of the key space as well as the trapdoor function being used. In order to satisfy the aforementioned constraints, there has been a growing interest over the past few years, in studying the behavior of chaotic systems and their applications in various fields such as data encryption due to characteristics like randomness, unpredictability and sensitivity of the generated sequence to the initial value and its parameters. This paper utilizes a novel 2D chaotic function that displays a uniform bifurcation over a large range of parameters and exhibits high levels of chaotic behavior to generate a random sequence that is used to encrypt the input data. The proposed method uses a genetic algorithm to optimize the parameters of the map to enhance security for any given textual data. Various analyses demonstrate an adequately large key space and the existence of multiple global optima indicating the necessity of the proposed system and the security provided by it.

Awnon Bhowmik, Unnikrishnan Menon

In recent years cyber-attacks are continuously developing. This means that hackers can find their way around the traditional cryptosystems. This calls for new and more secure cryptosystems to take their place. This paper outlines a new cryptosystem based on the dragon curve fractal. The security level of this scheme is based on multiple private keys, that are crucial for effective encryption and decryption of data. This paper discusses, how core concepts emerging from fractal geometry can be used as a trapdoor function for this cryptosystem.

Unnikrishnan Menon, Atharva Hudlikar, Divyani Panda

With the advent of quantum computing, and other advancements in computation and processing capabilities of modern systems, there arises a need to develop new trapdoor functions that will serve as the foundation for a new generation of encryption schemes. This paper explores the possibility of one such potential trapdoor function using concepts stemming from Reversible Cellular Automata (RCA) -- specifically, the Critter's Rule set up in a Margolus Neighborhood. The proposed block encryption algorithm discusses how sensitive data can be manipulated and converted efficiently into a two dimensional sequence of bits, that can be iteratively evolved using the rules of the RCA and a private key to achieve a desirable level of encryption within a reasonable runtime. The performance benchmark and analysis results exemplify how well the proposed encryption algorithm stands against different forms of attacks.