Related papers: Adjustable Privacy using Autoencoder-based Learnin…

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

Deep ensemble learning has been shown to improve accuracy by training multiple neural networks and averaging their outputs. Ensemble learning has also been suggested to defend against membership inference attacks that undermine privacy. In…

Differentially private optimization suffers from a fundamental geometric mismatch: deep networks have highly anisotropic loss landscapes, yet DP-SGD injects isotropic noise. Second-order preconditioning can resolve this, but estimating…

Traditional collaborative learning approaches are based on sharing of model weights between clients and a server. However, there are advantages to resource efficiency through schemes based on sharing of embeddings (activations) created from…

Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information. Nevertheless,…

Nowadays, more and more machine learning applications, such as medical diagnosis, online fraud detection, email spam filtering, etc., services are provided by cloud computing. The cloud service provider collects the data from the various…

Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how…

Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the…

Over the last decade, the use of Automatic Speaker Verification (ASV) systems has become increasingly widespread in response to the growing need for secure and efficient identity verification methods. The voice data encompasses a wealth of…

We consider the problem of obfuscating sensitive information while preserving utility, and we propose a machine learning approach inspired by the generative adversarial networks paradigm. The idea is to set up two nets: the generator, that…

Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of…

A critical concern in data-driven processes is to build models whose outcomes do not discriminate against some demographic groups, including gender, ethnicity, or age. To ensure non-discrimination in learning tasks, knowledge of the group…

Objective: To enable privacy-preserving learning of high quality generative and discriminative machine learning models from distributed electronic health records. Methods and Results: We describe general and scalable strategy to build…

The digital era has raised many societal challenges, including ICT's rising energy consumption and protecting privacy of personal data processing. This paper considers both aspects in relation to machine learning accuracy in an…

Learning from multiple sources of information is an important problem in machine-learning research. The key challenges are learning representations and formulating inference methods that take into account the complementarity and redundancy…

Tensor networks, widely used for providing efficient representations of low-energy states of local quantum many-body systems, have been recently proposed as machine learning architectures which could present advantages with respect to…

End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder extracts hidden features from raw sensor data, and the decoder outputs the…

We study privacy-utility trade-offs where users share privacy-correlated useful information with a service provider to obtain some utility. The service provider is adversarial in the sense that it can infer the users' private information…

Weakly-supervised anomaly detection aims at learning an anomaly detector from a limited amount of labeled data and abundant unlabeled data. Recent works build deep neural networks for anomaly detection by discriminatively mapping the normal…