Parsa Memarzadehsaghezi
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes RESSAP, a novel ensemble framework that significantly enhances the robustness of machine learning classifiers against adversarial evasion attacks by combining feature selection, ensemble prediction, and data augmentation.
The paper introduces SecRL-Prune, a structured reinforcement learning framework that effectively prunes CodeLLMs while preserving their critical ability to generate adversarial, functionality-preserving code mutations.
Papers
Robust Ensemble of Selectively Strengthened and Augmented Predictors
The paper proposes RESSAP, a novel ensemble framework that significantly enhances the robustness of machine learning classifiers against adversarial evasion attacks by combining feature selection, ens…