27 citations · 48 across the 10 of their papers we have counts for
10 papers
Towards Audit Requirements for AI-based Systems in Mobility Applications
Devi Padmavathi Alagarswamy, Christian Berghoff, Vasilios Danos +5
Various mobility applications like advanced driver assistance systems increasingly utilize artificial intelligence (AI) based functionalities. Typically, deep neural networks (DNNs…
Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
Lukas Schulth, Christian Berghoff, Matthias Neu
Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods…
Robustness testing of AI systems: A case study for traffic sign recognition
Christian Berghoff, Pavol Bielik, Matthias Neu +2
In the last years, AI systems, in particular neural networks, have seen a tremendous increase in performance, and they are now used in a broad range of applications. Unlike classic…
Protecting the integrity of the training procedure of neural networks
Christian Berghoff
Due to significant improvements in performance in recent years, neural networks are currently used for an ever-increasing number of applications. However, neural networks have the…
Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
Christian Berghoff, Matthias Neu, Arndt von Twickel
This article deals with the IT security of connectionist artificial intelligence (AI) applications, focusing on threats to integrity, one of the three IT security goals. Such threa…
Universal elliptic Gauß sums for Atkin primes in Schoof's algorithm
Christian J. Berghoff
This work builds on earlier results. We define universal elliptic Gauß sums for Atkin primes in Schoof's algorithm for counting points on elliptic curves. Subsequently, we show the…