Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers arxiv.org
Paper measures how cyber classifiers can stay right while their explanations drift, via ESI on Random Forest and XGBoost.
trending2
01 02 Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries arxiv.orgStudies membership leakage in tabular foundation models via attention, then adds an inference-time k-anonymity style defense. Lovely.