Celebrating Data Privacy Day at Private AI

What does privacy mean to us at Private AI? As a tech company whose purpose it is to enhance privacy, we are acutely aware of the value tension between businesses needing access to data to build amazing tools and the privacy interests of individual consumers. The privacy laws that have been enacted all over the … Read more

Why The Right To Be Forgotten Is Even Harder To Comply With Than You Think (And What To Do About It)

In today’s data-driven world, businesses are constantly collecting information from their customers in order to provide a better product or service, to understand and alleviate any pain points along their path to acquisition, to gain insights and create more efficient processes, and so much more. Data is often considered critical for modern organizations, but the … Read more

The Data Conundrum: Navigating Healthcare Privacy Legislation in Canada

The Canadian healthcare and health tech space is robust and growing at warp speed. Globally health tech, especially in the AI field, is evolving much faster than privacy legislation can keep pace. As such, with most sensitive of data at hand, this conundrum is becoming a complex space to navigate in the Canadian privacy legislative spectrum … Read more

Privacy in the Metaverse: Who is Responsible?

What is the Metaverse? Ever since the word “Metaverse” hit our vocabularies in 2021, there has been ample confusion with many publications trying their hands at making sense of what it means: “It may even be the case that any real “Metaverse” would be little more than some cool AR applications, VR games and digital … Read more

Top 7 Differential Privacy Papers for Language Modeling

Differential privacy is a hot topic given the many conflicting opinions on its effectiveness. For some background, we previously wrote a comprehensive post on the Basics of Differential Privacy where we discussed the risks and how it can also enhance natural language understanding (NLU) models.  The differential privacy papers in this post are just a … Read more

The Basics of Differential Privacy & Its Applicability to NLU Models

Over the years, large pre-trained language models like BERT and Roberta have led to significant improvements in natural language understanding (NLU) tasks. However, these pre-trained models pose a risk of potential data leakage if the training data includes any personally identifiable information (PII). To mitigate this risk, there are two common techniques to preserve privacy: … Read more

The Privacy Risk of Language Models

In today’s world, large models with billions of parameters trained on terabytes of datasets have become the norm as language models are the foundations of natural language processing (NLP) applications. Several of these language models used in commercial products are also being trained on private information. An example would be Gmail’s auto-complete model. Its model … Read more

When the Curious Abandon Honesty: Federated Learning Is Not Private

Previously on Private AI’s speaker series CEO, Patricia Thaine, sat down with Franziska Boenisch to discuss her latest paper, ‘When the Curious Abandon Honesty: Federated Learning Is Not Private’.  Franziska completed a Master’s degree in Computer Science at Freie University Berlin and Technical University Eindhoven. For the past 2.5 years, she has been working at Fraunhofer AISEC as a Research … Read more

9 Companies to Help You Get Your Privacy $hit Together

9 Companies to Help You Get Your Privacy $hit Together

With the ever-growing number of global regulations, legislations, and amendments, it can be overwhelming to know where to start (or continue) your data privacy journey. Below we’ve compiled a list of 9 companies who can help you build a proactive privacy, governance, and risk management strategy within your organization.  1. Establish your company’s privacy baseline … Read more


Testé sur un ensemble de données composé de données conversationnelles désordonnées contenant des informations de santé sensibles. Téléchargez notre livre blanc pour plus de détails, ainsi que nos performances en termes d’exactitude et de score F1, ou contactez-nous pour obtenir une copie du code d’évaluation.

99.5%+ Accuracy

Number quoted is the number of PII words missed as a fraction of total number of words. Computed on a 268 thousand word internal test dataset, comprising data from over 50 different sources, including web scrapes, emails and ASR transcripts.

Please contact us for a copy of the code used to compute these metrics, try it yourself here, or download our whitepaper.