174 citations · 313 across the 26 of their papers we have counts for
3 papers · 1 filter
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.…
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
Minghong Fang, Xiaoyu Cao, Jinyuan Jia +1
In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master dev…
Data Poisoning Attacks to Local Differential Privacy Protocols
Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong
Local Differential Privacy (LDP) protocols enable an untrusted data collector to perform privacy-preserving data analytics. In particular, each user locally perturbs its data to pr…