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

Add to Chrome

Add to Firefox

Picture for Neil Zhenqiang Gong

Neil Zhenqiang Gong

PointGuard: Provably Robust 3D Point Cloud Classification

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

Figure 1 for PointGuard: Provably Robust 3D Point Cloud Classification

Figure 2 for PointGuard: Provably Robust 3D Point Cloud Classification

Figure 3 for PointGuard: Provably Robust 3D Point Cloud Classification

Figure 4 for PointGuard: Provably Robust 3D Point Cloud Classification

* 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

Figure 1 for Data Poisoning Attacks and Defenses to Crowdsourcing Systems

Figure 2 for Data Poisoning Attacks and Defenses to Crowdsourcing Systems

Figure 3 for Data Poisoning Attacks and Defenses to Crowdsourcing Systems

Figure 4 for Data Poisoning Attacks and Defenses to Crowdsourcing Systems

* 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

Figure 1 for Provably Secure Federated Learning against Malicious Clients

Figure 2 for Provably Secure Federated Learning against Malicious Clients

Figure 3 for Provably Secure Federated Learning against Malicious Clients

Figure 4 for Provably Secure Federated Learning against Malicious Clients

* 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

Figure 1 for Data Poisoning Attacks to Deep Learning Based Recommender Systems

Figure 2 for Data Poisoning Attacks to Deep Learning Based Recommender Systems

Figure 3 for Data Poisoning Attacks to Deep Learning Based Recommender Systems

Figure 4 for Data Poisoning Attacks to Deep Learning Based Recommender Systems

* To appear in NDSS 2021

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

Figure 1 for FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

Figure 2 for FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

Figure 3 for FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

Figure 4 for FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

* 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

Figure 1 for Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks

Figure 2 for Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks

Figure 3 for Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks

Figure 4 for Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks

* 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

Figure 1 for Certified Robustness of Nearest Neighbors against Data Poisoning Attacks

Figure 2 for Certified Robustness of Nearest Neighbors against Data Poisoning Attacks

Figure 3 for Certified Robustness of Nearest Neighbors against Data Poisoning Attacks

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

Figure 1 for Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Figure 2 for Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Figure 3 for Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Figure 4 for Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

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

Figure 1 for Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes

Figure 2 for Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes

Figure 3 for Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes

Figure 4 for Robust and Verifiable Information Embedding Attacks to Deep Neural Networks via Error-Correcting Codes

* 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

Figure 1 for Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks

Figure 2 for Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks

Figure 3 for Intrinsic Certified Robustness of Bagging against Data Poisoning Attacks

Access Paper or Ask Questions

On the Intrinsic Differential Privacy of Bagging

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

Figure 1 for On the Intrinsic Differential Privacy of Bagging

Figure 2 for On the Intrinsic Differential Privacy of Bagging

Figure 3 for On the Intrinsic Differential Privacy of Bagging

Figure 4 for On the Intrinsic Differential Privacy of Bagging

Access Paper or Ask Questions

Backdoor Attacks to Graph Neural Networks

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

Figure 1 for Backdoor Attacks to Graph Neural Networks

Figure 2 for Backdoor Attacks to Graph Neural Networks

Figure 3 for Backdoor Attacks to Graph Neural Networks

Figure 4 for Backdoor Attacks to Graph Neural Networks

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

Figure 1 for Stealing Links from Graph Neural Networks

Figure 2 for Stealing Links from Graph Neural Networks

Figure 3 for Stealing Links from Graph Neural Networks

Figure 4 for Stealing Links from Graph Neural Networks

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

Figure 1 for On Certifying Robustness against Backdoor Attacks via Randomized Smoothing

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

Figure 1 for Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

Figure 2 for Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

Figure 3 for Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

Figure 4 for Influence Function based Data Poisoning Attacks to Top-N Recommender Systems

* 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

Figure 1 for Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

Figure 2 for Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

Figure 3 for Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

Figure 4 for Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing

* 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

Figure 1 for Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

Figure 2 for Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

Figure 3 for Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

* 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

Figure 1 for Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Figure 2 for Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Figure 3 for Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Figure 4 for Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

* 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

Figure 1 for IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

Figure 2 for IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

Figure 3 for IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

Figure 4 for IPGuard: Protecting the Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary

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

Figure 1 for MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

Figure 2 for MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

Figure 3 for MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

Figure 4 for MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples

* 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

Figure 1 for Defending against Machine Learning based Inference Attacks via Adversarial Examples: Opportunities and Challenges

* 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

Figure 1 for Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation

Figure 2 for Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation

Figure 3 for Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation

Figure 4 for Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation

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

Access Paper or Ask Questions