Related papers: Enabling Inference Privacy with Adaptive Noise Inj…

Diffusion-based purification (DBP) methods aim to remove adversarial noise from the input sample by first injecting Gaussian noise through a forward diffusion process, and then recovering the clean example through a reverse generative…

The process of data mining with differential privacy produces results that are affected by two types of noise: sampling noise due to data collection and privacy noise that is designed to prevent the reconstruction of sensitive information.…

Learning often involves sensitive data and as such, privacy preserving extensions to Stochastic Gradient Descent (SGD) and other machine learning algorithms have been developed using the definitions of Differential Privacy (DP). In…

The rise of deep learning has led to various successful attempts to apply deep neural networks (DNNs) for important networking tasks such as intrusion detection. Yet, running DNNs in the network control plane, as typically done in existing…

The remarkable success of machine learning, especially deep learning, has produced a variety of cloud-based services for mobile users. Such services require an end user to send data to the service provider, which presents a serious…

A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data. Existing defense mechanisms are not desirable to deploy in…

Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows while preserving privacy and minimizing energy consumption. Deep Neural Networks (DNNs) have been…

In 2011 Bhaskar et al. pointed out that in many cases one can ensure sufficient level of privacy without adding noise by utilizing adversarial uncertainty. Informally speaking, this observation comes from the fact that if at least a part of…

Spiking neural networks (SNNs) have emerged as prominent candidates for embedded and edge AI. Their inherent low power consumption makes them far more efficient than conventional ANNs in scenarios where energy budgets are tightly…

When applying machine learning to sensitive data, one has to find a balance between accuracy, information security, and computational-complexity. Recent studies combined Homomorphic Encryption with neural networks to make inferences while…

Membership Inference Attacks (MIAs) expose privacy risks by determining whether a specific sample was part of a model's training set. These threats are especially serious in sensitive domains such as healthcare and finance. Traditional…

In real-world applications, anomaly detection (AD) often operates without access to anomalous data, necessitating semi-supervised methods that rely solely on normal data. Among these methods, deep k-nearest neighbor (deep kNN) AD stands out…

We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a…

Deep neural networks (DNNs) are becoming more prevalent in important safety-critical applications, where reliability in the prediction is paramount. Despite their exceptional prediction capabilities, current DNNs do not have an implicit…

The collection of individuals' data has become commonplace in many industries. Local differential privacy (LDP) offers a rigorous approach to preserving privacy whereby the individual privatises their data locally, allowing only their…

Datasets are often used multiple times and each successive analysis may depend on the outcome of previous analyses. Standard techniques for ensuring generalization and statistical validity do not account for this adaptive dependence. A…

This paper proposes a locally differentially private federated learning algorithm for strongly convex but possibly nonsmooth problems that protects the gradients of each worker against an honest but curious server. The proposed algorithm…

Inference centers need more data to have a more comprehensive and beneficial learning model, and for this purpose, they need to collect data from data providers. On the other hand, data providers are cautious about delivering their datasets…

Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. Yet, this adaptability is vital for addressing user data privacy concerns. We address this limitation by storing…

Edge intelligence enables resource-demanding Deep Neural Network (DNN) inference without transferring original data, addressing concerns about data privacy in consumer Internet of Things (IoT) devices. For privacy-sensitive applications,…