4 citations · 15 across the 8 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.CR2021★ 4 cited
Universal 3-Dimensional Perturbations for Black-Box Attacks on Video Recognition Systems
Shangyu Xie, Han Wang, Yu Kong +1
Widely deployed deep neural network (DNN) models have been proven to be vulnerable to adversarial perturbations in many applications (e.g., image, audio and text classifications).…
cs.CR2021★ 2 cited
Privacy-preserving Cloud-based DNN Inference
Shangyu Xie, Bingyu Liu, Yuan Hong
Deep learning as a service (DLaaS) has been intensively studied to facilitate the wider deployment of the emerging deep learning applications. However, DLaaS may compromise the pri…