Today we’re joined by Nataniel Ruiz, a PhD Student in the Image & Video Computing group at Boston University.
We caught up with Nataniel to discuss his paper “Disrupting DeepFakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems,” which will be presented at the upcoming CVPR conference. In our conversation, we discuss the concept of this work, which essentially injects noise into an image to disrupt a generative model’s ability to manipulate said image. We also explore some of the challenging parts of implementing this work, a few potential scenarios in which this could be deployed, and the broader contributions that went into this work.
The complete show notes for this episode can be found at twimlai.com/talk/375.
Computer Vision for Remote AR with Flora Tasse - #390
Deep Learning for Automatic Basketball Video Production with Julian Quiroga - #389
How External Auditing is Changing the Facial Recognition Landscape with Deb Raji - #388
AI for High-Stakes Decision Making with Hima Lakkaraju - #387
Invariance, Geometry and Deep Neural Networks with Pavan Turaga - #386
Channel Gating for Cheaper and More Accurate Neural Nets with Babak Ehteshami Bejnordi - #385
Machine Learning Commerce at Square with Marsal Gavalda - #384
Cell Exploration with ML at the Allen Institute w/ Jianxu Chen - #383
Neural Arithmetic Units & Experiences as an Independent ML Researcher with Andreas Madsen - #382
2020: A Critical Inflection Point for Responsible AI with Rumman Chowdhury - #381
Panel: Advancing Your Data Science Career During the Pandemic - #380
On George Floyd, Empathy, and the Road Ahead
Engineering a Less Artificial Intelligence with Andreas Tolias - #379
Rethinking Model Size: Train Large, Then Compress with Joseph Gonzalez - #378
The Physics of Data with Alpha Lee - #377
Is Linguistics Missing from NLP Research? w/ Emily M. Bender - #376 🦜
Understanding the COVID-19 Data Quality Problem with Sherri Rose - #374
The Whys and Hows of Managing Machine Learning Artifacts with Lukas Biewald - #373
Language Modeling and Protein Generation at Salesforce with Richard Socher - #372
Create your
podcast in
minutes
It is Free
20/20
The Dropout
Ten Percent Happier with Dan Harris
World News Tonight with David Muir
NEJM This Week