5 papers · 1 filter
RL-FAT: Reinforcement Learning for Fair Adversarial Training
Tejaswini Medi, Levan Mikeladze, Margret Keuper
Deep neural networks remain highly vulnerable to adversarial perturbations, and adversarial training (AT) has become a widely used approach for improving robustness. However, impro…
Unsupervised Anomaly Detection Using Flow Matching on Tabular Data
Philip Konz, Tejaswini Medi, Margret Keuper
Financial anomaly detection often relies on large unlabeled transaction logs, where anomalous samples may already be present during training. Such training-set contamination violat…
TRIX- Trading Adversarial Fairness via Mixed Adversarial Training
Tejaswini Medi, Steffen Jung, Margret Keuper
Adversarial Training (AT) is a widely adopted defense against adversarial examples. However, existing approaches typically apply a uniform training objective across all classes, ov…
Towards Class-wise Robustness Analysis
Tejaswini Medi, Julia Grabinski, Margret Keuper
While being very successful in solving many downstream tasks, the application of deep neural networks is limited in real-life scenarios because of their susceptibility to domain sh…
FAIR-TAT: Improving Model Fairness Using Targeted Adversarial Training
Tejaswini Medi, Steffen Jung, Margret Keuper
Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges,…