7 citations · 11 across the 2 of their papers we have counts for
3 papers
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…
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…