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.
Understanding Cultural Style Trends with Computer Vision w/ Kavita Bala - #410
That's a VIBE: ML for Human Pose and Shape Estimation with Nikos Athanasiou, Muhammed Kocabas, Michael Black - #409
3D Deep Learning with PyTorch 3D w/ Georgia Gkioxari - #408
What are the Implications of Algorithmic Thinking? with Michael I. Jordan - #407
Beyond Accuracy: Behavioral Testing of NLP Models with Sameer Singh - #406
How Machine Learning Powers On-Demand Logistics at Doordash with Gary Ren - #405
Machine Learning as a Software Engineering Discipline with Dillon Erb - #404
AI and the Responsible Data Economy with Dawn Song - #403
Relational, Object-Centric Agents for Completing Simulated Household Tasks with Wilka Carvalho - #402
Model Explainability Forum - #401
What NLP Tells Us About COVID-19 and Mental Health with Johannes Eichstaedt - #400
Human-AI Collaboration for Creativity with Devi Parikh - #399
Neural Augmentation for Wireless Communication with Max Welling - #398
Quantum Machine Learning: The Next Frontier? with Iordanis Kerenidis - #397
ML and Epidemiology with Elaine Nsoesie - #396
Language (Technology) Is Power: Exploring the Inherent Complexity of NLP Systems with Hal Daumé III - #395
Graph ML Research at Twitter with Michael Bronstein - #394
Panel: The Great ML Language (Un)Debate! - #393
What the Data Tells Us About COVID-19 with Eric Topol - #392
The Case for Hardware-ML Model Co-design with Diana Marculescu - #391
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