72 citations · 405 across the 33 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.LG2019★ 34 cited
Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
Jinyuan Jia, Xiaoyu Cao, Binghui Wang +1
It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived.…
cs.CR2019★ 13 cited
Attacking Graph-based Classification via Manipulating the Graph Structure
Binghui Wang, Neil Zhenqiang Gong
Graph-based classification methods are widely used for security and privacy analytics. Roughly speaking, graph-based classification methods include collective classification and gr…