Stateful Detection of Black-Box Adversarial Attacks
Steven Chen, Nicholas Carlini, David Wagner
Abstract
The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even in the black-box threat model, as is the case in many practical settings. Here, the classifier is hosted as a remote service and the adversary does not have direct access to the model parameters.
Topics & Concepts
Adversarial systemComputer scienceStateful firewallBlack boxAdversaryComputer securityClassifier (UML)ObfuscationArtificial intelligenceAdversarial machine learningEvasion (ethics)Machine learningDenial-of-service attackWorld Wide WebThe InternetImmune systemBiologyImmunologyNetwork packetAdversarial Robustness in Machine LearningAdvanced Malware Detection TechniquesAnomaly Detection Techniques and Applications