Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the statistical power of predictive models, but creates an accessibility bias, where accuracy becomes inequitably distributed to those who have the resources to overcome these concerns. We present DISCO: an open-source DIStributed COllaborative learning platform accessible to non-technical users, offering a means to collaboratively build machine learning models without sharing any original data or requiring any programming knowledge. DISCO's web application trains models locally directly in the browser, making our tool cross-platform out-of-the-box, including smartphones. The modular design of \disco offers choices between federated and decentralized paradigms, various levels of privacy guarantees and several approaches to weight aggregation strategies that allow for model personalization and bias resilience in the collaborative training. Code repository is available at https://github.com/epfml/disco and a showcase web interface at https://discolab.ai

In our output perturbation method, the parties combine local models within a secure computation and then add the required differential privacy noise before revealing the model.

We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultaneously preserving privacy.

Merging datasets across institutions is a lengthy and costly procedure, especially when it involves private information. Data hosts may therefore want to prospectively gauge which datasets are most beneficial to merge with, without revealing sensitive information. For causal estimation this is particularly challenging as the value of a merge will depend not only on the reduction in epistemic uncertainty but also the improvement in overlap. To address this challenge, we introduce the first cryptographically secure information-theoretic approach for quantifying the value of a merge in the context of heterogeneous treatment effect estimation. We do this by evaluating the Expected Information Gain (EIG) and utilising multi-party computation to ensure it can be securely computed without revealing any raw data. As we demonstrate, this can be used with differential privacy (DP) to ensure privacy requirements whilst preserving more accurate computation than naive DP alone. To the best of our knowledge, this work presents the first privacy-preserving method for dataset acquisition tailored to causal estimation. We demonstrate the effectiveness and reliability of our method on a range of simulated and realistic benchmarks. The code is available anonymously.

Handling missing data is crucial in machine learning, but many datasets contain gaps due to errors or non-response. Unlike traditional methods such as listwise deletion, which are simple but inadequate, the literature offers more sophisticated and effective methods, thereby improving sample size and accuracy. However, these methods require accessing the whole dataset, which contradicts the privacy regulations when the data is distributed among multiple sources. Especially in the medical and healthcare domain, such access reveals sensitive information about patients. This study addresses privacy-preserving imputation methods for sensitive data using secure multi-party computation, enabling secure computations without revealing any party's sensitive information. In this study, we realized the mean, median, regression, and kNN imputation methods in a privacy-preserving way. We specifically target the medical and healthcare domains considering the significance of protection of the patient data, showcasing our methods on a diabetes dataset. Experiments on the diabetes dataset validated the correctness of our privacy-preserving imputation methods, yielding the largest error around $3 \times 10^{-3}$, closely matching plaintext methods. We also analyzed the scalability of our methods to varying numbers of samples, showing their applicability to real-world healthcare problems. Our analysis demonstrated that all our methods scale linearly with the number of samples. Except for kNN, the runtime of all our methods indicates that they can be utilized for large datasets.

Secure Multi-Party Computation (SMPC), as described by Wikipedia, is a subset of cryptography to create methods for multiple users to jointly compute a function over their inputs while keeping those inputs private. A significant benefit of Secure Multi-Party Computation is that it preserves data privacy while making it usable and open for analysis. I've explained how SecureMulti-Party Computation and Fair Multi-Party Computation work in earlier posts. While there are several emerging Use Cases of Secure Multi-Party Computation, I'm going to focus on three use cases in this post: autonomous vehicles and swarm robotics, healthcare data and analytics, and lastly, securely training machine learning models. Below are three use cases that would benefit from Secure Multi-Party Computation, i.e., being able to jointly compute a function over their inputs while keeping those inputs private.

We introduce a framework for navigating through cluttered environments by connecting multiple cameras together while simultaneously preserving privacy. Occlusions and obstacles in large environments are often challenging situations for navigation agents because the environment is not fully observable from a single camera view. Given multiple camera views of an environment, our approach learns to produce a multiview scene representation that can only be used for navigation, provably preventing one party from inferring anything beyond the output task. On a new navigation dataset that we will publicly release, experiments show that private multiparty representations allow navigation through complex scenes and around obstacles while jointly preserving privacy. Our approach scales to an arbitrary number of camera viewpoints. We believe developing visual representations that preserve privacy is increasingly important for many applications such as navigation.

AI and machine learning network Fetch.ai As mentioned in a blog post by Fetch.ai: "GLOW-DRB is a new decentralized random beacon that [aims to] provide incorruptible sources of randomness for decentralized applications. A "decentralized" Random Beacon is an "incorruptible" (cannot be altered by unauthorized or unapproved entities) and "unpredictable" source of randomness that is computed or calculated by several different parties in a manner that no individual or entity is able to interrupt or interfere with its calculation or "bias its value." These randomness techniques may be used in software programs that require the coordination of several different parties in environments that need high degrees of trust (for e.g., like in the finance or healthcare sectors). As explained by the Fetcha.ai DRB can, for instance, be used to determine which cryptocurrency trades may be matched in decentralized or non-custodial exchanges. The randomness values may also be used to deal cards in a "decentralized" game of poker, choose the winner of a lottery, or determine which service provider in a transport consortium should carry out a delivery. GLOW-DRB differs from the previous BLS scheme in its ability to achieve more reliable security levels known as pseudorandomness, which means that no single node can obtain any information on the random beacon value before other nodes have made their contribution to the multi-party computation."

PyTorch has become one of the most popular deep learning frameworks in the market and certainly a favorite of the research community when comes to experimentation. As a reference, PyTorch citations in papers on ArXiv grew 194 percent in the first half of 2019 alone, as noted by O'Reilly. For years, Facebook has based its deep learning work in a combination of PyTorch and Caffe2 and has put a lot of resources to support the PyTorch stack and developer community. Yesterday, Facebook released the latest version of PyTorch which showcases some state-of-the-art deep learning capabilities. There have been plenty of articles covering the launch of PyTorch 1.3.