Selected talks about our work on adversarial machine learning.

Can Machine Learning Ever Be Trustworthy?

University of Maryland, Booz Allen Hamilton Distinguished Colloquium. 7 December 2018. [SpeakerDeck] [Video]

Mutually Assured Destruction and the Impending AI Apocalypse

Keynote talk at USENIX Workshop of Offensive Technologies, Baltimore, Maryland, 13 August 2018.

Is “adversarial examples” an Adversarial Example?

David Evans’ keynote talk at the 1st Deep Learning and Security Workshop (co-located with the 39th IEEE Symposium on Security and Privacy). San Francisco, California. 24 May 2018.

Feature Squeezing

Weilin Xu’s talk at Network and Distributed System Security Symposium 2018. San Diego, CA. 21 February 2018.

Are We Playing the Wrong Game?

David Evans’ Talk at Berkeley ICSI, 8 June 2017.

Classifiers Under Attack

David Evans’ Talk at USENIX Enigma 2017, Oakland, CA, 1 February 2017. [Speaker Deck]

David Evans' Talk at O'Reilly Security 2016, New York City, 2 November 2016. [Speaker Deck]

Automatically Evading Classifiers

Weilin Xu’s Talk at NDSS 2016 (Blog Post)