Picture for Christian Berghoff

Christian Berghoff

Generative AI Models: Opportunities and Risks for Industry and Authorities

Add code
Jun 07, 2024
Viaarxiv icon

Towards Audit Requirements for AI-based Systems in Mobility Applications

Add code
Feb 27, 2023
Viaarxiv icon

Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering

Add code
Apr 27, 2022
Figure 1 for Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
Figure 2 for Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
Figure 3 for Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
Figure 4 for Detecting Backdoor Poisoning Attacks on Deep Neural Networks by Heatmap Clustering
Viaarxiv icon

Robustness testing of AI systems: A case study for traffic sign recognition

Add code
Aug 13, 2021
Figure 1 for Robustness testing of AI systems: A case study for traffic sign recognition
Figure 2 for Robustness testing of AI systems: A case study for traffic sign recognition
Figure 3 for Robustness testing of AI systems: A case study for traffic sign recognition
Figure 4 for Robustness testing of AI systems: A case study for traffic sign recognition
Viaarxiv icon

Protecting the integrity of the training procedure of neural networks

Add code
May 14, 2020
Figure 1 for Protecting the integrity of the training procedure of neural networks
Figure 2 for Protecting the integrity of the training procedure of neural networks
Viaarxiv icon

Vulnerabilities of Connectionist AI Applications: Evaluation and Defence

Add code
Mar 18, 2020
Figure 1 for Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
Figure 2 for Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
Figure 3 for Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
Figure 4 for Vulnerabilities of Connectionist AI Applications: Evaluation and Defence
Viaarxiv icon