Machine Learning (ML) has recently shown tremendous success in modeling various healthcare prediction tasks, ranging from disease diagnosis and prognosis to patient treatment. Due to the sensitive nature of medical data, privacy must be considered along the entire ML pipeline, from model training to inference. In this paper, we conduct a review of recent literature concerning Privacy-Preserving Machine Learning (PPML) for healthcare. We primarily focus on privacy-preserving training and inference-as-a-service, and perform a comprehensive review of existing trends, identify challenges, and discuss opportunities for future research directions. The aim of this review is to guide the development of private and efficient ML models in healthcare, with the prospects of translating research efforts into real-world settings.

The biggest benchmarking data set to date for a machine learning technique designed with data privacy in mind has been released open source by researchers at the University of Michigan. Called federated learning, the approach trains learning models on end-user devices, like smartphones and laptops, rather than requiring the transfer of private data to central servers. "By training in-situ on data where it is generated, we can train on larger real-world data," explained Fan Lai, U-M doctoral student in computer science and engineering, who presents the FedScale training environment at the International Conference on Machine Learning this week. "This also allows us to mitigate privacy risks and high communication and storage costs associated with collecting the raw data from end-user devices into the cloud," Lai said. Still a new technology, federated learning relies on an algorithm that serves as a centralized coordinator.

Virtual assortment of user devices provides a realistic training environment for distributed machine learning, protects privacy by learning where …

Heading into 2021, the future of artificial intelligence (AI) in technology and cybersecurity will only continue to evolve as more organizations adopt new and innovative techniques. According to one recent survey, two-thirds of organizations are already using the intelligent technology for cybersecurity purposes. Using these tools allows for companies to be more prepared for the innovative attacks that cybercriminals continue to develop – also using AI technologies. For example, just last year, criminals employed AI-based software to replicate a CEO's voice to command a cash transfer of €220,000 (approximately $243,000). For businesses looking to implement more AI into their security stack in 2021, it's important to follow these six steps to ensure the effective use of AI – without compromising security anywhere else down the line.

We use gradient sparsification to reduce the adverse effect of differential privacy noise on performance of private machine learning models. To this aim, we employ compressed sensing and additive Laplace noise to evaluate differentially-private gradients. Noisy privacy-preserving gradients are used to perform stochastic gradient descent for training machine learning models. Sparsification, achieved by setting the smallest gradient entries to zero, can reduce the convergence speed of the training algorithm. However, by sparsification and compressed sensing, the dimension of communicated gradient and the magnitude of additive noise can be reduced. The interplay between these effects determines whether gradient sparsification improves the performance of differentially-private machine learning models. We investigate this analytically in the paper. We prove that, for small privacy budgets, compression can improve performance of privacy-preserving machine learning models. However, for large privacy budgets, compression does not necessarily improve the performance. Intuitively, this is because the effect of privacy-preserving noise is minimal in large privacy budget regime and thus improvements from gradient sparsification cannot compensate for its slower convergence.

Janssen Research & Development seeks to drive innovation and deliver transformational medicines for the treatment of diseases in six therapeutic areas: neuroscience, cardiovascular diseases and metabolism, infectious diseases, immunology, oncology and pulmonary hypertension. In these areas, Janssen aims to address and solve unmet medical needs through the development of small and large molecules, as well as vaccines. The Janssen campus in Beerse (Belgium) has a unique ecosystem covering the complete drug development life cycle, with all capabilities from basic science to market access on one campus. The integrated environment of our campus gives our people the chance to experience many different aspects of drug development throughout their career. It has a successful track record of over sixty years of drug discovery and development and is one of the most important innovation engines of the Janssen group worldwide.

Given the reliance of artificial intelligence on machine learning, and of machine learning on data, the conventional wisdom is that privacy and A.I. are fundamentally at odds--progress in one must come at the expense of the other. Advancing both A.I. and privacy, however, is not a zero-sum game. Researchers from academia and industry have been marrying ideas from cryptography and machine learning to provide the seemingly paradoxical ability to learn from data without seeing it. Suppose that a group of hospitals wants to build a machine learning system that analyzes patient data and estimates the likelihood of disease. In theory, by sharing their data, they could build a more accurate model, but privacy rules forbid this.