papers

Publications (24)

cs.LG2019

Sample Efficient Adaptive Text-to-Speech

Yutian Chen, Yannis Assael, Brendan Shillingford +11

We present a meta-learning approach for adaptive text-to-speech (TTS) with few data. During training, we learn a multi-speaker model using a shared conditional WaveNet core and ind…

cs.LG2020

Neither Private Nor Fair: Impact of Data Imbalance on Utility and Fairness in Differential Privacy

Tom Farrand, Fatemehsadat Mireshghallah, Sahib Singh +1

Deployment of deep learning in different fields and industries is growing day by day due to its performance, which relies on the availability of data and compute. Data is often cro…

cs.LG2022

An automatic differentiation system for the age of differential privacy

Dmitrii Usynin, Alexander Ziller, Moritz Knolle +4

We introduce Tritium, an automatic differentiation-based sensitivity analysis framework for differentially private (DP) machine learning (ML). Optimal noise calibration in this set…

cs.CR2025

Private Map-Secure Reduce: Infrastructure for Efficient AI Data Markets

Sameer Wagh, Kenneth Stibler, Shubham Gupta +8

The modern AI data economy centralizes power, limits innovation, and misallocates value by extracting data without control, privacy, or fair compensation. We introduce Private Map-…

cs.LG2020

Benchmarking Differentially Private Residual Networks for Medical Imagery

Sahib Singh, Harshvardhan Sikka, Sasikanth Kotti +1

In this paper we measure the effectiveness of -Differential Privacy (DP) when applied to medical imaging. We compare two robust differential privacy mechanisms: Local-DP and DP…

cs.AI2023

Exploring the Relevance of Data Privacy-Enhancing Technologies for AI Governance Use Cases

Emma Bluemke, Tantum Collins, Ben Garfinkel +1

The development of privacy-enhancing technologies has made immense progress in reducing trade-offs between privacy and performance in data exchange and analysis. Similar tools for…

cs.CY2023

UN Handbook on Privacy-Preserving Computation Techniques

David W. Archer, Borja de Balle Pigem, Dan Bogdanov +10

This paper describes privacy-preserving approaches for the statistical analysis. It describes motivations for privacy-preserving approaches for the statistical analysis of sensitiv…

cs.CY2025

Personhood credentials: Artificial intelligence and the value of privacy-preserving tools to distinguish who is real online

Steven Adler, Zoë Hitzig, Shrey Jain +29

Anonymity is an important principle online. However, malicious actors have long used misleading identities to conduct fraud, spread disinformation, and carry out other deceptive sc…

cs.CR2024

Beyond Privacy Trade-offs with Structured Transparency

Andrew Trask, Emma Bluemke, Teddy Collins +5

Successful collaboration involves sharing information. However, parties may disagree on how the information they need to share should be used. We argue that many of these concerns…

cs.LG2022

DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?

Archit Uniyal, Rakshit Naidu, Sasikanth Kotti +4

Recent advances in differentially private deep learning have demonstrated that application of differential privacy, specifically the DP-SGD algorithm, has a disparate impact on dif…

cs.CY2020

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Miles Brundage, Shahar Avin, Jasmine Wang +56

With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations an…

cs.CY2024

The Ethics of Advanced AI Assistants

Iason Gabriel, Arianna Manzini, Geoff Keeling +54

This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural langu…

cs.CY2025

Open Problems in Technical AI Governance

Anka Reuel, Ben Bucknall, Stephen Casper +30

AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at…

cs.LG2018

Scaling shared model governance via model splitting

Miljan Martic, Jan Leike, Andrew Trask +3

Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation. Unfortunately, neither of these techniqu…

cs.LG2021

Syft 0.5: A Platform for Universally Deployable Structured Transparency

Adam James Hall, Madhava Jay, Tudor Cebere +20

We present Syft 0.5, a general-purpose framework that combines a core group of privacy-enhancing technologies that facilitate a universal set of structured transparency systems. Th…

cs.CR2020

Privacy-preserving medical image analysis

Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel +8

The utilisation of artificial intelligence in medicine and healthcare has led to successful clinical applications in several domains. The conflict between data usage and privacy pr…

cs.LG2021

Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation

Alexander Ziller, Dmitrii Usynin, Moritz Knolle +6

In recent years, formal methods of privacy protection such as differential privacy (DP), capable of deployment to data-driven tasks such as machine learning (ML), have emerged. Rec…

cs.NE2018

Neural Arithmetic Logic Units

Andrew Trask, Felix Hill, Scott Reed +3

Neural networks can learn to represent and manipulate numerical information, but they seldom generalize well outside of the range of numerical values encountered during training. T…

cs.CY2021

The Future of Digital Health with Federated Learning

Nicola Rieke, Jonny Hancox, Wenqi Li +14

Data-driven Machine Learning has emerged as a promising approach for building accurate and robust statistical models from medical data, which is collected in huge volumes by modern…

cs.CL2015

Modeling Order in Neural Word Embeddings at Scale

Andrew Trask, David Gilmore, Matthew Russell

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level dis…

cs.CR2021

Towards General-purpose Infrastructure for Protecting Scientific Data Under Study

Andrew Trask, Kritika Prakash

The scientific method presents a key challenge to privacy because it requires many samples to support a claim. When samples are commercially valuable or privacy-sensitive enough, t…

cs.CY2025

Beyond Release: Access Considerations for Generative AI Systems

Irene Solaiman, Rishi Bommasani, Dan Hendrycks +4

Generative AI release decisions determine whether system components are made available, but release does not address many other elements that change how users and stakeholders are…

cs.CL2015

sense2vec - A Fast and Accurate Method for Word Sense Disambiguation In Neural Word Embeddings

Andrew Trask, Phil Michalak, John Liu

Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationship…

cs.LG2018

A generic framework for privacy preserving deep learning

Theo Ryffel, Andrew Trask, Morten Dahl +4

We detail a new framework for privacy preserving deep learning and discuss its assets. The framework puts a premium on ownership and secure processing of data and introduces a valu…