Related papers: Transformers -- Messages in Disguise
Machine learning (ML) is widely used today, especially through deep neural networks (DNNs), however, increasing computational load and resource requirements have led to cloud-based solutions. To address this problem, a new generation of…
Stochastic Neural Networks (SNNs) that inject noise into their hidden layers have recently been shown to achieve strong robustness against adversarial attacks. However, existing SNNs are usually heuristically motivated, and often rely on…
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…
We establish connections between the Transformer architecture, originally introduced for natural language processing, and Graph Neural Networks (GNNs) for representation learning on graphs. We show how Transformers can be viewed as message…
We propose adversarial embedding, a new steganography and watermarking technique that embeds secret information within images. The key idea of our method is to use deep neural networks for image classification and adversarial attacks to…
One of the key requirement of many schemes is that of random numbers. Sequence of random numbers are used at several stages of a standard cryptographic protocol. A simple example is of a Vernam cipher, where a string of random numbers is…
In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that…
Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the…
The problem of error-control in random linear network coding is considered. A ``noncoherent'' or ``channel oblivious'' model is assumed where neither transmitter nor receiver is assumed to have knowledge of the channel transfer…
Machine learning algorithms based on deep neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy…
RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction…
Resistive memory (RM) based neuromorphic systems can emulate synaptic plasticity and thus support continual learning, but they generally lack biologically inspired mechanisms for active forgetting, which are critical for meeting modern data…
Machine learning has become a key tool in cybersecurity, improving both attack strategies and defense mechanisms. Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated high accuracy in detecting malware…
Encryption-based attacks have introduced significant challenges for detection mechanisms that rely on predefined signatures, heuristic indicators, or static rule-based classifications. Probabilistic Latent Encryption Mapping presents an…
Deep neural networks are vulnerable to adversarial examples, which are crafted by adding small, human-imperceptible perturbations to the original images, but make the model output inaccurate predictions. Before deep neural networks are…
Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…
Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing…
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction…
In this work, we present a novel matrix-encoding method that is particularly convenient for neural networks to make predictions in a privacy-preserving manner using homomorphic encryption. Based on this encoding method, we implement a…
Recent years have seen an increasing involvement of Deep Learning in the cryptanalysis of various ciphers. The present study is inspired by past works on differential distinguishers, to develop a Deep Neural Network-based differential…