Adversarial example detection based on saliency map features
Shen Wang, Yuxin Gong
Topics & Concepts
InterpretabilityComputer scienceAdversarial systemArtificial intelligenceBlack boxMachine learningProcess (computing)Interpretation (philosophy)Deep neural networksImage (mathematics)Artificial neural networkPattern recognition (psychology)Programming languageOperating systemAdversarial Robustness in Machine LearningExplainable Artificial Intelligence (XAI)Anomaly Detection Techniques and Applications