Events

Sign up for our mailing list to stay up to date with our upcoming events and news

Previous Webinars

Launching Privacy-Preserving ML Projects with Private AI and LivePerson 

Cybersecurityand Privacy in Government in the Age of AI with Microsoft Canada

Play Video

Discussing ‘Language Modelling via Learning to Rank’ with Arvid Frydenlund

Play Video

Discussing ‘When the Curious Abandon Honesty: Federated Learning Is Not Private’ with Franziska Boenisch

Play Video

MLOps & Machine Learning Deployment at Scale with Luke de Oliveira

Play Video

Parameter Predictions and Training Without SGD ft. Prof. Graham Taylor

Play Video

Data Privacy, Law, and Cybersecurity with Carole Piovesan

Play Video

An Interview with Sheila Jambekar, CPO at Plaid

Play Video

Talking with Dr. Ann Cavoukian, Privacy by Design Inventor

Past Speaking Engagements

Our co-founders are leading experts on privacy-preserving natural language processing, machine learning edge deployment, model optimization, and more. Check out some of their past speaking engagements below. Interested in booking for them for your event, podcast, or publication? Contact us.

In Conversation with Patricia Thaine – CEO and Co-founder of Private AI
Privacy Podcast
Responsible AI, Tech Startup Journey & Funding Panel
Women in AI Ethics
The Importance of Privacy in NLP
World Summit AI Americas 
Deploying Transformers at Scale: Addressing Challenges and Increasing Performance

Machine Learning Prague 

AIP Podcast Episode 5 – Patricia Thaine, CEO of Private AI

AI Partnerships Corp. Podcast 

The Need for AI Privacy with Patricia Thaine, CEO of Private AI

Vux World Podcast

AI’s Wild West: Ethics and Artificial Intelligence

Communitech Critical Tech Talk 

Demystifying the De-Identification of Data – How to Protect your Organization’s Data

Canadian RegTech Association

Your privacy is my currency with Patricia Thaine

Catalog & Cocktails Podcast

Privacy Tech Talk: Private AI

Privacy Tech Talk Podcast

Developer Challenges in Preserving Privacy

Caveat Podcast

Deploying Transformers at Scale: Addressing Challenges and Increasing Performance

Toronto Machine Learning Summit

Big Data & Analytics Strategy at the Heart of Cybersecurity and Privacy

Toronto Machine Learning Summit

Additional talks and panels include:  

The Importance of Privacy in NLP (May 5, 2022), World Summit AI Americas  
An Overview of Privacy-Preserving NLP (February 17, 2022), guest lecture at the University of Washington.

Dealing with Personal Data using AI (December 15, 2021), at the Better Ethics and Consumer Outcomes Network’s Fireside Chat.
Privacy-Enhancing Technologies in AI Security (December 1, 2021), at O’Reilly Media’s AI Superstream Series: Securing AI.
Panel: Big Data and Analytics Strategy at the Heart of Cybersecurity and Privacy (November 18, 2021), at Toronto Machine Learning Summit.
Panel: Demystifying the De-identification of Data (November 16, 2021), at The Innovation Game: Adopting RegTech in a Digital Age, Canadian Regulatory Technology Association.
Panel: Can voices be anonymised? (November 2, 2021), Lorentz Workshop on Speech as Personable Identifiable Information.
The Latest Advances in Privacy-Preserving NLP (September 21, 2021), Toronto Machine Leaning Summit on NLP.
Privacy Preserving Synthetic Data in AI/ML – A Mirage. (June 2, 2021), Privacy Symposium 2021 (Infosys – IAPP).
Efficient Evaluation of Activation Functions over Encrypted Data (January 15, 2021), UofT AI Conference.
Private-Preserving Machine Learning (December 3, 2020), MLOps: Production and Engineering Vancouver 2020.
Cybersecurity and Privacy: Complements for a more secure Internet (November 25, 2020), Keynote talk at Vector Institute Endless Summer School (ESS).
Panel moderator for The Role of ML in Climate Change (November 18, 2020), at Toronto Machine Learning Summit.
Privacy in Deployment (October 16, 2020), 2020 USENIX Conference on Privacy Engineering Practice and Respect (PEPR’20).
A Practical Guide to Privacy-Preserving Machine Learning (November 12, 2020), EVOKE CASCON 2020.
Privacy in Production (June 30, 2020), Canada AI/ML, Data Science and Engineering Digital Meetup.
Privacy-Preserving Machine Learning (June 18, 2020), MLOps: Production and Engineering World.
Privacy-Preserving Machine Learning: A Practical Overview (June 10, 2020), Vector Institute Endless Summer School (ESS).
An Overview of the Problem of Perfectly Privacy-Preserving AI (June 8, 2020), Future of Privacy Forum AI Working Group.
Privacy-Preserving Natural Language Processing Using Homomorphic Encryption (2019), National Research Council of Canada, Ottawa, CA.
Privacy-Preserving Natural Language Processing Using Homomorphic Encryption (2019), Borealis AI, Toronto, CA.
Perfectly Privacy-Preserving AI: What is it and how do we achieve it? (2019), Identity, Privacy, and Security Institute, Toronto.
Privacy-Preserving Natural Language Processing (2018), Vector Institute for Artificial Intelligence, Toronto, CA.
Vowel and Consonant Classification through Spectral Decomposition (2017), National Research Council of Canada, Ottawa, CA.

Stay in the loop

Sign up for our mailing list to stay up to date with our upcoming webinars, news, and more!

Download the Free Report

Request an API Key

Fill out the form below and we’ll send you a free API key for 500 calls (approx. 50k words). No commitment, no credit card required!

Language Packs

Expand the categories below to see which languages are included within each language pack.
Note: English capabilities are automatically included within the Enterprise pricing tier. 

French
Spanish
Portuguese

Arabic
Hebrew
Persian (Farsi)
Swahili

French
German
Italian
Portuguese
Russian
Spanish
Ukrainian
Belarusian
Bulgarian
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
Greek
Hungarian
Icelandic
Latvian
Lithuanian
Luxembourgish
Polish
Romanian
Slovak
Slovenian
Swedish
Turkish

Hindi
Korean
Tagalog
Bengali
Burmese
Indonesian
Khmer
Japanese
Malay
Moldovan
Norwegian (Bokmål)
Punjabi
Tamil
Thai
Vietnamese
Mandarin (simplified)

Arabic
Belarusian
Bengali
Bulgarian
Burmese
Catalan
Croatian
Czech
Danish
Dutch
Estonian
Finnish
French
German
Greek
Hebrew
Hindi
Hungarian
Icelandic
Indonesian
Italian
Japanese
Khmer
Korean
Latvian
Lithuanian
Luxembourgish
Malay
Mandarin (simplified)
Moldovan
Norwegian (Bokmål)
Persian (Farsi)
Polish
Portuguese
Punjabi
Romanian
Russian
Slovak
Slovenian
Spanish
Swahili
Swedish
Tagalog
Tamil
Thai
Turkish
Ukrainian
Vietnamese

Rappel

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.