news category icon

Adversarial Examples

Post Date: 24. May 2018

Deep neural networks have given rise to great hopes and expectations for new applications in safety-critical areas such as automotive, healthcare or finance. However, to have society gain confidence in  the technology, we must minimize the often unintuitive behavior of deep neural networks. Can you trust a machine that confuses pedestrians with a free road, dust with cancer or an economic crisis with a bullish market? We are able to manipulate images, sound waves and even 3D-printed objects that can cause your well-trained model with allegedly superhuman performance to fail, while people will not notice any difference from the original data. The future doesn’t look so bright any more, does it? Yes, it does – with neurocat. Meow!

In the first step we let your model fail once, in the second step we make sure it will succeed forever after.

You may also find this interesting

Hands on Guide to comply with ECJ ruling

Hands on Guide to comply with ECJ ruling

In this article we want to propose a strategy on how to satisfy legal constraints AI is facing right now. The ruling of the European Court of Justice (ECJ), on the 21st of July 2022, is a perfect example that empathizes the need for transparency and risk evaluation...

Germany takes enormous leap towards safe autonomous driving.

Germany takes enormous leap towards safe autonomous driving.

KI-Absicherung positions Germany for the new key technologies and market leadership of the German automotive industry with regard to automated driving. We were part of the „KI Absicherung“ research project that is part of the Federal Government’s AI strategy, which...

neurocat and the Rise of AI

neurocat and the Rise of AI

On the 8th of June 2022 Florens Gressner  (CEO of neurocat) had the opportunity to talk at the Rise of AI Conference 2022, the most influential platform in the AI Industry. He talks about the upcoming AI Act that will...

neurocat wins 1st place award at TechAD 2022

neurocat wins 1st place award at TechAD 2022

Neurocat won 1st place in Software and Compute Category at the 2022 edition of the Tech.AD EUROPE AWARD. The Tech.AD Europe Award exclusively honours extraordinary projects in the automotive industry and celebrates exceptional solutions & innovations. “The winners...

neurocat donates 3.600€ to support Ukrainian refugees

neurocat donates 3.600€ to support Ukrainian refugees

On the 24th of February, Putin announced the start of his contemptible and unjustified military operation on the Ukraine. We from neurocat believe this is also an attack on peace itself and on the fundamental rights that we share with our Ukrainian brothers and...

neurocat CEO Florens Greßner in IHK Berlin Magazine

neurocat CEO Florens Greßner in IHK Berlin Magazine

Our CEO Florens Greßner featured in IHK Berlin magazine’s February 2022 edition talking about his inspiration for #neurocat, love for abstract #mathematics and advice for #young #entrepreneurs 📰 Check out the magazine below (#35, only in German) 👇🏻...

neurocat Honoured With Vision Award 2021

neurocat Honoured With Vision Award 2021

Neurocat was awarded with the VisionAward 2021 at MedienTage Munich. VisionAwards have been given to young and established companies and entrepreneurs who set new trends with a new business idea. The jury for the award consisted of interdisciplinary experts and...

dSPACE Acquires Interests in Berlin Start-Up neurocat

dSPACE Acquires Interests in Berlin Start-Up neurocat

dSPACE, an internationally leading provider of simulation and validation solutions for the development of networked, self-driving, and electric vehicles, has acquired interests in neurocat. Support from a renowned industry leader will give us the necessary support in...

Wasserstein Verification Paper Published

Wasserstein Verification Paper Published

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...

5
4

Start Your Own Newsworthy Project!