Related papers: Non-Rival Data as Rival Products: An Encapsulation…

The proliferation of the Internet of Things (IoT) and widespread use of devices with sensing, computing, and communication capabilities have motivated intelligent applications empowered by artificial intelligence. The classical artificial…

Data privacy is a major concern in industries such as healthcare or finance. The requirement to safeguard privacy is essential to prevent data breaches and misuse, which can have severe consequences for individuals and organisations.…

With the rising adoption of Machine Learning across the domains like banking, pharmaceutical, ed-tech, etc, it has become utmost important to adopt responsible AI methods to ensure models are not unfairly discriminating against any group.…

Over the last few years, machine learning unlocked previously infeasible features for compression, such as providing guarantees for users' privacy or tailoring compression to specific data statistics (e.g., satellite images or audio…

When machine learning models are trained on synthetic data and then deployed on real data, there is often a performance drop due to the distribution shift between synthetic and real data. In this paper, we introduce a new ensemble strategy…

Organizations are increasingly relying on data to support decisions. When data contains private and sensitive information, the data owner often desires to publish a synthetic database instance that is similarly useful as the true data,…

Machine unlearning without access to real data distribution is challenging. The existing method based on data-free distillation achieved unlearning by filtering out synthetic samples containing forgetting information but struggled to…

Data assimilation combines information from models, measurements, and priors to estimate the state of a dynamical system such as the atmosphere. The Ensemble Kalman filter (EnKF) is a family of ensemble-based data assimilation approaches…

Data for good implies unfettered access to data. But data owners must be conservative about how, when, and why they share data or risk violating the trust of the people they aim to help, losing their funding, or breaking the law. Data…

Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained by a central server that orchestrates the FL training…

Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing…

Sensitive medical data is often subject to strict usage constraints. In this paper, we trained a generative adversarial network (GAN) on real-world electronic health records (EHR). It was then used to create a data-set of "fake" patients…

Homomorphic encryption is a very useful gradient protection technique used in privacy preserving federated learning. However, existing encrypted federated learning systems need a trusted third party to generate and distribute key pairs to…

Federated learning is an emerging distributed machine learning framework aiming at protecting data privacy. Data heterogeneity is one of the core challenges in federated learning, which could severely degrade the convergence rate and…

Adversarial attacks on face recognition systems (FRSs) pose serious security and privacy threats, especially when these systems are used for identity verification. In this paper, we propose a novel method for generating adversarial…

Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabelled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to…

Anomaly and missing data constitute a thorny problem in industrial applications. In recent years, deep learning enabled anomaly detection has emerged as a critical direction, however the improved detection accuracy is achieved with the…

Despite unconditional feature inversion being the foundation of many image synthesis applications, training an inverter demands a high computational budget, large decoding capacity and imposing conditions such as autoregressive priors. To…

The rapid growth of data from edge devices has catalyzed the performance of machine learning algorithms. However, the data generated resides at client devices thus there are majorly two challenge faced by traditional machine learning…

Existing quantization aware training methods attempt to compensate for the quantization loss by leveraging on training data, like most of the post-training quantization methods, and are also time consuming. Both these methods are not…