Lune

Profiles2020-2023

Xiaoyu Cao

Duke University

12Papers
2Last author
9Unique co-authors
5First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers12

  1. FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical InformationAuthor 1 of 5S&P 2023
  2. FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious ClientsAuthor 2 of 4KDD 2022 · 293 citations
  3. Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor AttacksAuthor 3 of 3AAAI 2022 · 90 citations
  4. Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial PerturbationsAuthor 3 of 5ICLR 2022 · 26 citations
  5. Poisoning Attacks to Local Differential Privacy Protocols for Key-Value DataAuthor 1 of 3USENIX Security 2022
  6. Provably Secure Federated Learning against Malicious ClientsAuthor 1 of 3AAAI 2021 · 161 citations
  7. Intrinsic Certified Robustness of Bagging against Data Poisoning AttacksAuthor 2 of 2AAAI 2021 · 155 citations
  8. Data Poisoning Attacks to Local Differential Privacy ProtocolsAuthor 1 of 3USENIX Security 2021 · 100 citations
  9. Certified Robustness of Graph Neural Networks against Adversarial Structural PerturbationAuthor 3 of 4KDD 2021 · 50 citations
  10. FLTrust: Byzantine-robust Federated Learning via Trust BootstrappingAuthor 1 of 4NDSS 2021
  11. Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized SmoothingAuthor 2 of 4ICLR 2020 · 107 citations
  12. Local Model Poisoning Attacks to Byzantine-Robust Federated LearningAuthor 2 of 4USENIX Security 2020
Dusk over the sea between two cliffs drawn in fine vertical lines