Semantic Adversarial Deep Learning
Sanjit A. Seshia, Somesh Jha, Tommaso Dreossi
Abstract
Adversarial examples have emerged as a key threat for machine-learning-based systems, especially the ones that employ deep neural networks. Unlike a large body of research in this area, this Keynote article accounts for the semantic, context, and specifications of the complete system with machine learning components in resource-constrained environments. -Muhammad Shafique, Technische Universität Wien.
Topics & Concepts
Adversarial systemDeep learningComputer scienceArtificial intelligenceKey (lock)Context (archaeology)Deep neural networksResource (disambiguation)Artificial neural networkNatural language processingCognitive scienceMachine learningPsychologyComputer securityHistoryComputer networkArchaeologyAdversarial Robustness in Machine LearningAdvanced Malware Detection TechniquesAnomaly Detection Techniques and Applications