Inconspicuous Adversarial Patches for Fooling Image Recognition Systems on Mobile Devices
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2021.3124815
Abstract: Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples, called… read more here.
Keywords: inconspicuous adversarial; adversarial patches; recognition systems; image ... See more keywords
Minipatch: Undermining DNN-Based Website Fingerprinting With Adversarial Patches
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2022.3186743
Abstract: Website Fingerprinting (WF) enables a local passive attacker to infer which website a user is visiting over an encrypted connection. Classifiers utilizing deep neural networks (DNNs) automatically extract reliable features and have achieved up to… read more here.
Keywords: dnn based; undermining dnn; based website; website fingerprinting ... See more keywords