Transcription of Practical Black-Box Attacks against Machine Learning
{{id}} {{{paragraph}}}
Example: barber
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. We introduce the firstpractical demonstration of an attacker controlling a remotelyhosted DNN with no such knowledge. Indeed, the only capa-bility of our Black-Box adversary is to observe labels givenby the DNN to chosen inputs. Our attack strategy consistsin training a local model to substitute for the target DNN,using inputs synthetically generated by an adversary andlabeled by the target DNN.
Practical Black-Box Attacks against Machine Learning Nicolas Papernot Pennsylvania State University ngp5056@cse.psu.edu Patrick …
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
Related search queries
Artificial intelligence and machine learning, Artificial intelligence and machine learning in financial services, Gaussian Processes for Machine Learning, Systems, Unit 4 Test Student Class, Unit 4 Test _____ _____ Student Class, Machine, Pipeline Optimization Tool for Automating Machine Learning, Failure prediction and process monitoring, Failure prediction and process monitoring using Machine Learning