RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.
Explaining and harnessing adversarial examples
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
AI media detectors with AUC near 0.99 in clean conditions suffer major accuracy and calibration drops under platform transforms and visually constrained adversarial attacks.
citing papers explorer
-
Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
RAAT harmonizes clean accuracy and adversarial robustness by using fixed reduced perturbations for boundary samples and Domain Interpolation Consistency Adversarial Regularization to align input and latent spaces.
-
The Deployment Gap in AI Media Detection: Platform-Aware and Visually Constrained Adversarial Evaluation
AI media detectors with AUC near 0.99 in clean conditions suffer major accuracy and calibration drops under platform transforms and visually constrained adversarial attacks.