Related papers: InfoShape: Task-Based Neural Data Shaping via Mutu…

This paper investigates, from information theoretic grounds, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact features from data, i.e., using fewer bits than needed to…

Deep neural network (DNN)-based joint source and channel coding is proposed for privacy-aware end-to-end image transmission against multiple eavesdroppers. Both scenarios of colluding and non-colluding eavesdroppers are considered. Unlike…

In-context learning (ICL) has shown promising improvement in downstream task adaptation of LLMs by augmenting prompts with relevant input-output examples (demonstrations). However, the ICL demonstrations can contain privacy-sensitive…

Machine learning models require datasets for effective training, but directly sharing raw data poses significant privacy risk such as membership inference attacks (MIA). To mitigate the risk, privacy-preserving techniques such as data…

This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference.…

Enabling robots to learn novel visuomotor skills in a data-efficient manner remains an unsolved problem with myriad challenges. A popular paradigm for tackling this problem is through leveraging large unlabeled datasets that have many…

Motivated by privacy issues caused by inference attacks on user activities in the packet sizes and timing information of Internet of Things (IoT) network traffic, we establish a rigorous event-level differential privacy (DP) model on…

We study the problem of data release with privacy, where data is made available with privacy guarantees while keeping the usability of the data as high as possible --- this is important in health-care and other domains with sensitive data.…

Deep learning systems have been reported to achieve state-of-the-art performances in many applications, and a key is the existence of well trained classifiers on benchmark datasets. As a main-stream loss function, the cross entropy can…

Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…

Exponential models of distributions are widely used in machine learning for classiffication and modelling. It is well known that they can be interpreted as maximum entropy models under empirical expectation constraints. In this work, we…

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

Classification and segmentation are crucial in medical image analysis as they enable accurate diagnosis and disease monitoring. However, current methods often prioritize the mutual learning features and shared model parameters, while…

Machine learning (ML) holds great potential for accurately forecasting treatment outcomes over time, which could ultimately enable the adoption of more individualized treatment strategies in many practical applications. However, a…

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate…

Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services but suffer from…

Machine Learning (ML) for information security (InfoSec) utilizes distinct data types and formats which require different treatments during optimization/training on raw data. In this paper, we implement a malicious/benign URL predictor…

Mutual information (MI) is a fundamental measure of statistical dependence between two variables, yet accurate estimation from finite data remains notoriously difficult. No estimator is universally reliable, and common approaches fail in…

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

Due to data privacy constraints, data sharing among multiple clinical centers is restricted, which impedes the development of high performance deep learning models from multicenter collaboration. Naive weight transfer methods share…