3 papers
cs.LG2024
Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System
Julian Collado, Kevin Stangl
Recent approaches in machine learning often solve a task using a composition of multiple models or agentic architectures. When targeting a composed system with adversarial attacks,…
cs.LG2024
Fairness, Accuracy, and Unreliable Data
Kevin Stangl
This thesis investigates three areas targeted at improving the reliability of machine learning; fairness in machine learning, strategic classification, and algorithmic robustness.…
cs.CV2024
Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation
Kevin Stangl, Marius Arvinte, Weilin Xu +1
Zero-shot anomaly segmentation using pre-trained foundation models is a promising approach that enables effective algorithms without expensive, domain-specific training or fine-tun…