Niklas Bunzel

According to our database, Niklas Bunzel authored at least 26 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2025

Quantifying the Risk of Transferred Black Box Attacks.

Disesdi Susanna Cox, Niklas Bunzel

CoRR, November, 2025

The Relationship Between Network Similarity and Transferability of Adversarial Attacks.

Gerrit Klause, Niklas Bunzel

CoRR, January, 2025

Exploring the Relationship Between Network Similarity and Transferability of Adversarial Attacks.

Gerrit Klause, Niklas Bunzel

Proceedings of the 24th IEEE International Conference on Trust, 2025

Evasion Attacks in Continual Learning.

Niklas Bunzel, Aino Schwarte

Proceedings of the 24th IEEE International Conference on Trust, 2025

Compliance Made Practical: Translating the EU AI Act into Implementable Security Actions.

Niklas Bunzel

Proceedings of the IEEE/ACM International Workshop on Responsible AI Engineering, 2025

Team RoMa @ AADD-2025: On the Generation of Transferable and Visually Imperceptible Adversarial Attacks Against Deepfake Detectors.

Nicolas Göller, Lukas Graner, Raphael Antonius Frick, Niklas Bunzel

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Adversarial Attack Challenge for Secure Face Recognition 2025.

João Tremoço, Iurii Medvedev, Nuno R. Freitas, Andreia M. Costa, Diogo Nunes, Niklas Bunzel, Lukas Graner, Nicholas Göller, Lorenzo Pellegrini, Nicolò Di Domenico, Guido Borghi, Monson Verghese, Shruti Bhilare, Avik Hati, Miguel Lourenço, Nuno Gonçalves

Proceedings of the IEEE International Joint Conference on Biometrics, 2025

On the Transferability of Adversarial Attacks from Convolutional Neural Networks to Variants of ChatGPT4.

Niklas Bunzel

Proceedings of the 55th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2025

2024

Analyzing the Effectiveness of Image Preprocessing Defenses Under Runtime Constraints.

Niklas Bunzel, Gerrit Klause

Proceedings of the 23rd IEEE International Conference on Trust, 2024

Identifying and Generating Edge Cases.

Niklas Bunzel, Nicolas Göller, Raphael Antonius Frick

Proceedings of the 2nd ACM Workshop on Secure and Trustworthy Deep Learning Systems, 2024

Signals Are All You Need: Detecting and Mitigating Digital and Real-World Adversarial Patches Using Signal-Based Features.

Niklas Bunzel, Raphael Antonius Frick, Gerrit Klause, Aino Schwarte, Jonas Honermann

Proceedings of the 2nd ACM Workshop on Secure and Trustworthy Deep Learning Systems, 2024

Bridging the Gap: The Role of OWASP AI Exchange in AI Standardization.

Niklas Bunzel, Nicolas Göller

Proceedings of the 54. Jahrestagung der Gesellschaft für Informatik, 2024

Adversarial Patch Detection: Leveraging Depth Contrast for Enhanced Threat Visibility.

Niklas Bunzel, Jannis Hamborg

Proceedings of the 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2024

Measuring the Effects of Environmental Influences on Object Detection.

Niklas Bunzel, Michel Geißler, Gerrit Klause

Proceedings of the 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2024

Patching the Cracks: Detecting and Addressing Adversarial Examples in Real-World Applications.

Niklas Bunzel

Proceedings of the 54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2024

2023

Multi-class Detection for Off The Shelf transfer-based Black Box Attacks.

Niklas Bunzel, Dominic Böringer

Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop, 2023

Predicting positions of flipped bits in robust image hashes.

Marius Leon Hammann, Martin Steinebach, Huajian Liu, Niklas Bunzel

Proceedings of the Media Watermarking, 2023

Detection of deepfakes using background-matching.

Stephanie Blümer, Martin Steinebach, Raphael Antonius Frick, Niklas Bunzel

Proceedings of the Media Watermarking, 2023

Adversarial Patch Detection and Mitigation by Detecting High Entropy Regions.

Niklas Bunzel, Ashim Siwakoti, Gerrit Klause

Proceedings of the 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2023

A Concise Analysis of Pasting Attacks and their Impact on Image Classification.

Niklas Bunzel, Lukas Graner

Proceedings of the 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks, 2023

2022

Face Pasting Attack.

Niklas Bunzel, Lukas Graner

CoRR, 2022

Robust face recognition: How much face Is needed?

Niklas Bunzel

Proceedings of the Media Watermarking, 2022

Using Telegram as a carrier for image steganography: Analysing Telegrams API limits.

Niklas Bunzel, Tobias Chen, Martin Steinebach

Proceedings of the ARES 2022: The 17th International Conference on Availability, Reliability and Security, Vienna,Austria, August 23, 2022

2021

Cover-aware Steganalysis.

Niklas Bunzel, Martin Steinebach, Huajian Liu

J. Cyber Secur. Mobil., 2021

Adversarial Examples zum Selbstdatenschutz? Der Fall biometrischer Gesichtserkennung im öffentlichen Raum.

Niklas Bunzel, Neele Zander, Robert Landwirth, Ann-Katrin Riedel

Proceedings of the 51. Jahrestagung der Gesellschaft für Informatik, INFORMATIK 2021 - Computer Science & Sustainability, Berlin, Germany, 27. September, 2021

2020

Non-blind steganalysis.

Niklas Bunzel, Martin Steinebach, Huajian Liu

Proceedings of the ARES 2020: The 15th International Conference on Availability, 2020