Related papers: Transformers -- Messages in Disguise
Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…
This project involves an implementation of the Rivest Shamir Adleman (RSA) encryption algorithm in C. It consists of generation of two random prime numbers and a number co- prime to phi(n) also called euler toitent function. These three are…
In general, Graph Neural Networks(GNN) have been using a message passing method to aggregate and summarize information about neighbors to express their information. Nonetheless, previous studies have shown that the performance of graph…
In this paper, we propose a novel method for enhancing security in privacy-preserving federated learning using the Vision Transformer. In federated learning, learning is performed by collecting updated information without collecting raw…
Convolutional neural network is a machine-learning model widely applied in various prediction tasks, such as computer vision and medical image analysis. Their great predictive power requires extensive computation, which encourages model…
What is the computational model behind a Transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, Transformers have no…
This paper proposes a video encryption algorithm using RSA and Pseudo Noise (PN) sequence, aimed at applications requiring sensitive video information transfers. The system is primarily designed to work with files encoded using the Audio…
The goal of any cryptographic system is the exchange of information among the intended users without any leakage of information to others who may have unauthorized access to it. A common secret key could be created over a public channel…
Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue…
The remarkable success of machine learning has fostered a growing number of cloud-based intelligent services for mobile users. Such a service requires a user to send data, e.g. image, voice and video, to the provider, which presents a…
This paper considers rateless network error correction codes for reliable multicast in the presence of adversarial errors. Most existing network error correction codes are designed for a given network capacity and maximum number of errors…
Spiking Neural Networks (SNNs) have received widespread attention due to their unique neuronal dynamics and low-power nature. Previous research empirically shows that SNNs with Poisson coding are more robust than Artificial Neural Networks…
We consider a set of $n$ messages and a group of $k$ clients. Each client is privileged for receiving an arbitrary subset of the messages over a broadcast erasure channel, which generalizes scenario of a previous work. We propose a method…
We present a framework for the design of coding mechanisms that allow remotely operating anomaly detectors in a privacy-preserving manner. We consider the following problem setup. A remote station seeks to identify anomalies based on system…
A key challenge for Deep Neural Network (DNN) algorithms is their vulnerability to adversarial attacks. Inherently non-deterministic compute substrates, such as those based on Analog In-Memory Computing (AIMC), have been speculated to…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
Deep neural networks have become widely used, obtaining remarkable results in domains such as computer vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, and…
Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks…
Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation…
Machine learning models have been successfully applied to a wide range of applications including computer vision, natural language processing, and speech recognition. A successful implementation of these models however, usually relies on…