Transcription of Practical Black-Box Attacks against Machine Learning
{{id}} {{{paragraph}}}
Example: bankruptcy
Practical Black-Box Attacks against Machine Learning
Practical Black-Box Attacks against Machine LearningNicolas PapernotPennsylvania State McDanielPennsylvania State Goodfellow JhaUniversity of Berkay CelikPennsylvania State SwamiUS Army Research Learning (ML) models, , deep neural networks(DNNs), are vulnerable to adversarial examples: maliciousinputs modified to yield erroneous model outputs, while ap-pearing unmodified to human observers. Potential attacksinclude having malicious content like malware identified aslegitimate or controlling vehicle behavior. Yet, all existingadversarial example Attacks require knowledge of either themodel internals or its training data.
demonstrated control of models created for our own account. 2. ABOUT DEEP NEURAL NETWORKS ... We focus on classi cation tasks, where the goal is to assign inputs a label among a prede- ned set of labels. The DNN is given a large set of known ... The DNN outputs are identi ed below the samples.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: