Transcription of Practical Black-Box Attacks against Machine Learning
{{id}} {{{paragraph}}}
Example: confidence
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.
through transformations of the physical tra c sign. Related works showed the feasibility of such physical transformations for a state-of-the-art vision classi er [6] and face recognition model [11]. It is thus conceivable that physical adversarial tra c signs could be generated by maliciously modifying the sign itself, e.g., with stickers or paint.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: