Videos

Here are some selected videos of talks about our research.

Inference Risks for Machine Learning

Invited talk at the Distributed and Private Machine Learning (DPML) workshop at ICLR 2021, 7 May 2021. [Video]

When Models Learn Too Much

CrySP Speaker Series on Privacy, University of Waterloo, 29 March 2021. [Abstract] [Video]

Hybrid Batch Attacks

Suya’s presentation on Hybrid Batch Attacks at USENIX Security 2020:

(Download Video [mp4], Blog Post, Paper: [PDF] [arXiv])

Empirically Measuring Concentration

Xiao Zhang’s presentation at NeurIPS 2019:
https://slideslive.com/38921718/track-2-session-1 (starting at 26:50)

Evaluating Differentially Private Machine Learning in Practice

Bargav Jayaraman’s talk at USENIX Security 2019:

Can Machine Learing Ever By Trustworthy?

University of Maryland, Booz Allen Hamilton Distinguished Colloquium at the University of Maryland, 7 December 2018.

Video: Can Machine Learning Ever Be Trustworthy? [SpeakerDeck]

Is “adversarial examples” an Adversarial Example?

Keynote talk at 1st Deep Learning and Security Workshop (Co-located with the 39th IEEE Symposium on Security and Privacy). San Francisco, California. 24 May 2018 (includes an intro on GDPR going into effect!). [SpeakerDeck]

Enigma: Classifiers Under Attack

Talk at USENIX Enigma 2017, Oakland, CA, 1 February 2017. [Speaker Deck] [Blog Post]