State-of-the-art neural networks are vulnerable to adversarial examples. This major problem for the safe deployment of ML models arises when minor inp...
Read more
Robustness Verification: Seminar Presentation at HU Berlin
- Research
- November 15, 2018
Two of our cats are soon going to give a talk about the current status of duality-based adversarial robustness verification. The content will strongly rely on the recent publication ”Training Verified Learners with Learned Verifiers” by K. Dvijotham et al. (DeepMind). If you are as excited about this topic as we are – take a look at the attached presentation draft!
This could also be interesting for you
Times of Growth
Since the beginning of 2019, neurocat’s manpower has more than doubled. With all teams growing fast, we significantly expanded our office space. Luc...
Read more
Techcode Pitch Won
The world’s leading trade show for industrial technology and AI: Hannover Messe, Germany. With 6,500 exhibitors and over 250,000 visitors, it’...
Read more
Robustness Verificat...
Two of our cats are soon going to give a talk about the current status of duality-based adversarial robustness verification. The content will strongly...
Read more
Interview Adlershof-...
What is growth? The Adlershof Journal examined beliefs about growth and interviewed us about AI security and our personal growth story. After a conver...
Read more
Website launched
After a year of hard and exciting work the time has come for a first small website! Today we launched the first version of the site and plan to fill i...
Read more
Phone
+49 (0)30 34065918Skype: neurocat GmbH