We are proud to present our joint work with the University of Göttingen. Formal verification of neural networks is a challenging topic! In the past, ...
Read more
Wasserstein Verification Paper Published
- Research
- October 15, 2021
We are proud to present our joint work with the University of Göttingen. Formal verification of neural networks is a challenging topic! In the past, verification methods were mainly focused on Lp-norms for measuring imperceptibility. Using Lp-norms for measuring the size of noise fails to capture human similarity perception, which is why measures like the Wasserstein metric are increasingly being used in the field of adversarial robustness.
We were now able to develop a formal verification framework for the highly complex Wasserstein metric. Furthermore, we present a simple Wasserstein attack, which generates adversarial data 16x faster than previous benchmark attacks.
We recommend the reading: https://arxiv.org/pdf/2110.06816.pdf
This could also be interesting for you
Papercat Thursday 12...
Proud to present the research paper contributed by colleagues at neurocat GmbH & Volkswagen AG. Risk Assessment for ML models is of paramount impo...
Read more
Decision Boundary
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 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
Phone
+49 (0) 30 340 65 918Skype: neurocat GmbH