Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Neil Zhenqiang Gong

PointGuard: Provably Robust 3D Point Cloud Classification


Mar 04, 2021
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

* To appear in CVPR 2021 

  Access Paper or Ask Questions

Data Poisoning Attacks and Defenses to Crowdsourcing Systems


Feb 24, 2021
Minghong Fang, Minghao Sun, Qi Li, Neil Zhenqiang Gong, Jin Tian, Jia Liu

* To appear in the Web Conference 2021 (WWW '21) 

  Access Paper or Ask Questions

Provably Secure Federated Learning against Malicious Clients


Feb 16, 2021
Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

* Accepted by AAAI-21 

  Access Paper or Ask Questions

Data Poisoning Attacks to Deep Learning Based Recommender Systems


Jan 08, 2021
Hai Huang, Jiaming Mu, Neil Zhenqiang Gong, Qi Li, Bin Liu, Mingwei Xu

* To appear in NDSS 2021 

  Access Paper or Ask Questions

Practical Blind Membership Inference Attack via Differential Comparisons


Jan 07, 2021
Bo Hui, Yuchen Yang, Haolin Yuan, Philippe Burlina, Neil Zhenqiang Gong, Yinzhi Cao


  Access Paper or Ask Questions

FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping


Dec 27, 2020
Xiaoyu Cao, Minghong Fang, Jia Liu, Neil Zhenqiang Gong

* To appear in NDSS 2021 

  Access Paper or Ask Questions

Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks


Dec 25, 2020
Binghui Wang, Jinyuan Jia, Neil Zhenqiang Gong

* Accepted by AAAI 2021 

  Access Paper or Ask Questions

Certified Robustness of Nearest Neighbors against Data Poisoning Attacks


Dec 07, 2020
Jinyuan Jia, Xiaoyu Cao, Neil Zhenqiang Gong


  Access Paper or Ask Questions

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations


Nov 15, 2020
Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong


  Access Paper or Ask Questions

Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes


Oct 26, 2020
Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong

* Accepted by AsiaCCS'21 

  Access Paper or Ask Questions

Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks


Sep 04, 2020
Jinyuan Jia, Xiaoyu Cao, Neil Zhenqiang Gong


  Access Paper or Ask Questions

On the Intrinsic Differential Privacy of Bagging


Aug 22, 2020
Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong


  Access Paper or Ask Questions

Backdoor Attacks to Graph Neural Networks


Jun 19, 2020
Zaixi Zhang, Jinyuan Jia, Binghui Wang, Neil Zhenqiang Gong


  Access Paper or Ask Questions

Stealing Links from Graph Neural Networks


May 05, 2020
Xinlei He, Jinyuan Jia, Michael Backes, Neil Zhenqiang Gong, Yang Zhang


  Access Paper or Ask Questions

On Certifying Robustness against Backdoor Attacks via Randomized Smoothing


Feb 26, 2020
Binghui Wang, Xiaoyu Cao, Jinyuan jia, Neil Zhenqiang Gong


  Access Paper or Ask Questions

Influence Function based Data Poisoning Attacks to Top-N Recommender Systems


Feb 19, 2020
Minghong Fang, Neil Zhenqiang Gong, Jia Liu

* Accepted by WWW 2020; This is technical report version 

  Access Paper or Ask Questions

Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing


Feb 09, 2020
Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Neil Zhenqiang Gong

* Accepted by WWW'20; This is technical report version 

  Access Paper or Ask Questions

Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing


Dec 20, 2019
Jinyuan Jia, Xiaoyu Cao, Binghui Wang, Neil Zhenqiang Gong

* ICLR 2020, code is available at this: https://github.com/jjy1994/Certify_Topk 

  Access Paper or Ask Questions

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning


Nov 26, 2019
Minghong Fang, Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong

* The paper was submitted to Usenix Security Symposium in February 2019 and will appear in Usenix Security Symposium 2020 

  Access Paper or Ask Questions

IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary


Oct 30, 2019
Xiaoyu Cao, Jinyuan Jia, Neil Zhenqiang Gong


  Access Paper or Ask Questions

MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples


Sep 26, 2019
Jinyuan Jia, Ahmed Salem, Michael Backes, Yang Zhang, Neil Zhenqiang Gong

* To appear in CCS'19 

  Access Paper or Ask Questions

Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges


Sep 19, 2019
Jinyuan Jia, Neil Zhenqiang Gong

* Book chapter. arXiv admin note: substantial text overlap with arXiv:1805.04810 

  Access Paper or Ask Questions

Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation


Dec 06, 2018
Binghui Wang, Jinyuan Jia, Neil Zhenqiang Gong

* To appear in the 26th Annual Network and Distributed System Security Symposium (NDSS), Feb 2019 

  Access Paper or Ask Questions