Skip to content

Author

Niklas Bunzel

We have 3 of 31 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Catastrophic Learning: A New Attack Vector on Continual Learning Networks

The results demonstrate a strong vulnerability: an adversary can selectively impede plasticity to hinder the acquisition of new knowledge, while promoting loss of prior knowledge, inducing a catastrophic learning scenario.

Benedikt Kluss, Niklas Bunzel · 0 citations
Jul 2026

VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness

It is argued that future robustness evaluations should report vanilla-referenced accuracy gaps as a standard component, and demonstrated that the robustness-accuracy trade-off is substantially larger than what is typically conveyed by individual papers.

Niklas Bunzel · 0 citations
Preprint Jul 2026

Detecting Adversarial Evasion Attacks Against Autoencoder-Based Network Intrusion Detection Systems

Two complementary detectors are proposed: the Residual Localisation Detector (RLD), which tracks the spatial concentration of reconstruction errors in the inter-arrival time feature region in image space; and the Feature-Space Perturbation Consistency (FPC) Detector, which operates directly on packet-level inter-arriva...

Niklas Bunzel, Ashim Siwakoti · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.