← Search

Hai (Helen) Li

2 accepted papers

2019

Feature Space Perturbations Yield More Transferable Adversarial Examples

CVPR 2019poster

Many recent works have shown that deep learning models are vulnerable to quasi-imperceptible input perturbations, yet practitioners cannot fully explain this behavior. This work describes a transfer-based blackbox targeted adversarial attack of deep feature space representations that also provides i…

Cited by 239PDFScholar
2017

A Compact DNN: Approaching GoogLeNet-Level Accuracy of Classification and Domain Adaptation

CVPR 2017poster

Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An emerging question, however, is whether these model compressio…

Cited by 71PDFScholar