6 papers
Catastrophic Learning: A New Attack Vector on Continual Learning Networks
Benedikt Kluss, Niklas Bunzel
Continual Learning (CL) enables deep learning models to iteratively learn from a stream of data without forgetting prior knowledge. Existing adversarial research on CL primarily ai…
VanillaBench: The Hidden Accuracy Cost of Adversarial Robustness
Niklas Bunzel
Adversarial robustness research has produced hundreds of defended models over the past decade, yet the literature almost universally reports robustness results in isolation: standa…
Detecting Adversarial Evasion Attacks Against Autoencoder-Based Network Intrusion Detection Systems
Niklas Bunzel, Ashim Siwakoti
Evasion attacks deliberately manipulate input to an ML-based system to produce an incorrect prediction while the manipulated input still appears benign. The PANDA framework has dem…
Quantifying the Risk of Transferred Black Box Attacks
Disesdi Susanna Cox, Niklas Bunzel
Neural networks have become pervasive across various applications, including security-related products. However, their widespread adoption has heightened concerns regarding vulnera…
The Relationship Between Network Similarity and Transferability of Adversarial Attacks
Gerrit Klause, Niklas Bunzel
Neural networks are vulnerable to adversarial attacks, and several defenses have been proposed. Designing a robust network is a challenging task given the wide range of attacks tha…
Face Pasting Attack
Niklas Bunzel, Lukas Graner
Cujo AI and Adversa AI hosted the MLSec face recognition challenge. The goal was to attack a black box face recognition model with targeted attacks. The model returned the confiden…