Podorbit
DiscoverPodcastsGuestsCompanies
Podorbit

Tech podcasts · indexed by guest & company

PrivacyTermsSupport
support@podorbit.app
University of Tübingen

University of Tübingen

uni-tuebingen.de →

People from University of Tübingen

Matthias Bethge

Professor

Wieland Brendel

Researcher

Episodes featuring University of Tübingen (2)

Machine Learning Street Talk (MLST)/Jan 31, 2021/1h 36m

#040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr)

Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. there's good reason to believe neural networks look at very different features than we would have expected. As articulated in the 2019 "features not bugs" paper Adversarial examples can be directly attributed to the presence of non-robust features: features derived from patterns in the data distribution that are highly predictive, yet brittle and incomprehensible to humans. Adversarial examples don't just affect deep learning models. A cottage industry has sprung up around Threat Modeling in AI and ML Systems and their dependencies. Joining us this evening are some of currently leading researchers in adversarial examples; Florian Tramèr - A fifth year PhD student in Computer Science at Stanford University https://floriantramer.com/​ https://twitter.com/florian_tramer​ Dr. Wieland Brendel - Machine Learning Researcher at the University of Tübingen & Co-Founder of layer7.ai https://medium.com/@wielandbr​ https://twitter.com/wielandbr​ Dr. Nicholas Carlini - Research scientist at Google Brain working in that exciting space between machine learning and computer security. https://nicholas.carlini.com/​ We really hope you enjoy the conversation, remember to subscribe! Yannic Intro [00:00:00​] Tim Intro [00:04:07​] Threat Taxonomy [00:09:00​] Main show intro [00:11:30​] Whats wrong with Neural Networks? [00:14:52​] The role of memorization [00:19:51​] Anthropomorphization of models [00:22:42​] Whats the harm really though / focusing on actual ML security risks [00:27:03​] Shortcut learning / OOD generalization [00:36:18​] Human generalization [00:40:11​] An existential problem in DL getting the models to learn what we want? [00:41:39​] Defenses to adversarial examples [00:47:15​] What if we had all the data and the labels? Still problems? [00:54:28​] Defenses are easily broken [01:00:24​] Self deception in academia [01:06:46​] ML Security [01:28:15​] https://www.youtube.com/watch?v=2PenK06tvE4

Nicholas Carlini

Research Scientist, Google DeepMind

Google DeepMindGoogle DeepMindGoogle BrainGoogle Brain
Wieland Brendel

Researcher

University of TübingenUniversity of Tübingen
Florian Tramèr

PhD Researcher

Stanford UniversityStanford University
Eye On A.I./Feb 5, 2019/22m

Episode 8 - Bernhard Schölkopf & Matthias Bethge

In this episode of Eye on AI, I continue my review of AI research in different regions of the world with a focus on Europe. Europe, with its strong academic tradition, faces unique challenges in scientific research because of the continent's fragmentation and the weakening of the European Union. Given the growing dominance of North America and China, Europe risks being left behind. To understand what Europe is doing to avoid this, I talk to Bernhard Schölkopf and Matthias Bethge, two machine learning researchers from Tübingen, Germany, who have been working to bring machine learning research in Europe under one umbrella. I hope you find Bernhard and Matthias as interesting as I did.

Bernhard Schölkopf

Director

Max Planck Institute for Intelligent SystemsMax Planck Institute for Intelligent Systems
Matthias Bethge

Professor

University of TübingenUniversity of Tübingen