2 papers
cs.LG2025
Volatility in Certainty (VC): A Metric for Detecting Adversarial Perturbations During Inference in Neural Network Classifiers
Vahid Hemmati, Ahmad Mohammadi, Abdul-Rauf Nuhu +3
Adversarial robustness remains a critical challenge in deploying neural network classifiers, particularly in real-time systems where ground-truth labels are unavailable during infe…
cs.LG2025
A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness
Abdul-Rauf Nuhu, Parham Kebria, Vahid Hemmati +4
Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversari…