Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks
Z. Chen, Pritam Dash, Karthik Pattabiraman
Abstract
Adversarial patch attacks create adversarial examples by injecting arbitrary distortions within a bounded region of the input to fool deep neural networks (DNNs). These attacks are robust (i.e., physically-realizable) and universally malicious, and hence represent a severe security threat to real-world DNN-based systems.
Topics & Concepts
Adversarial systemDeep neural networksComputer scienceBounded functionArtificial neural networkArtificial intelligenceComputer securityMathematicsMathematical analysisAdversarial Robustness in Machine LearningAnomaly Detection Techniques and ApplicationsAdvanced Malware Detection Techniques