Related papers: Unsupervised Information Obfuscation for Split Inf…

Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sensitive data in pre-trained models without retraining from…

Deep learning models are increasingly utilized on resource-constrained edge devices for real-time data analytics. Recently, Vision Transformer and their variants have shown exceptional performance in various computer vision tasks. However,…

We propose split-brain autoencoders, a straightforward modification of the traditional autoencoder architecture, for unsupervised representation learning. The method adds a split to the network, resulting in two disjoint sub-networks. Each…

Semi-supervised learning is a challenging problem which aims to construct a model by learning from limited labeled examples. Numerous methods for this task focus on utilizing the predictions of unlabeled instances consistency alone to…

Uncertainty estimation is crucial for machine learning models to detect out-of-distribution (OOD) inputs. However, the conventional discriminative deep learning classifiers produce uncalibrated closed-set predictions for OOD data. A more…

Face anonymization aims to conceal identity information while preserving non-identity attributes. Mainstream diffusion models rely on inference-time interventions such as negative guidance or energy-based optimization, which are applied…

Many Internet-of-Things (IoT) devices rely on cloud computation resources to perform machine learning inferences. This is expensive and may raise privacy concerns for users. Consumers of these devices often have hardware such as gaming…

In split inference, a deep neural network (DNN) is partitioned to run the early part of the DNN at the edge and the later part of the DNN in the cloud. This meets two key requirements for on-device machine learning: input privacy and…

The rapid rise of IoT and Big Data has facilitated copious data driven applications to enhance our quality of life. However, the omnipresent and all-encompassing nature of the data collection can generate privacy concerns. Hence, there is a…

Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication…

We develop and approach to unsupervised semantic medical image segmentation that extends previous work with generative adversarial networks. We use existing edge detection methods to construct simple edge diagrams, train a generative model…

This paper investigates the piracy problem of deep learning models. Designing and training a well-performing model is generally expensive. However, when releasing them, attackers may reverse engineer the models and pirate their design. This…

In network analysis, the core structure of modeling interest is usually hidden in a larger network in which most structures are not informative. The noise and bias introduced by the non-informative component in networks can obscure the…

Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarely studied due to the…

Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…

Unsupervised video object segmentation aims to segment a target object in the video without a ground truth mask in the initial frame. This challenging task requires extracting features for the most salient common objects within a video…

In edge intelligence, deep learning~(DL) models are deployed at an edge device and an edge server for data processing with low latency in the Internet of Things~(IoT). In this letter, we propose a new end-to-end learning-based wireless…

Distributed DNN inference is becoming increasingly important as the demand for intelligent services at the network edge grows. By leveraging the power of distributed computing, edge devices can perform complicated and resource-hungry…

Despite encryption, the packet size is still visible, enabling observers to infer private information in the Internet of Things (IoT) environment (e.g., IoT device identification). Packet padding obfuscates packet-length characteristics…

Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…