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
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
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
Data privacy, in simplest terms, is the right to control how your personal information is collected and used. Although this may seem obvious, it hasn’t always been the case. With data being generated in mass amounts daily, it’s interesting that the earliest data protection laws like the Data Protection Act only started to emerge in … Read more
GDPR compliance, privacy and engineering team collaboration, and common mistakes companies make with their data.
Discussing developer responsibility, Bill C-11, positive consent, and the importance of Privacy by Design
“When is anonymization useful?” is a tricky question, because the answer is highly data-type- and task-dependent.
On the misleading ways journalists and industry use the term “anonymization.”
Regexes are highly effective in the perfect world of computer data, but unfortunately the real world is much more complicated.
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.
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.
