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 Lingjuan Lyu

Anti-Backdoor Learning: Training Clean Models on Poisoned Data


Oct 25, 2021
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

* Accepted to NeurIPS 2021 

  Access Paper or Ask Questions

How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data


Sep 03, 2021
Zhiyuan Zhang, Lingjuan Lyu, Weiqiang Wang, Lichao Sun, Xu Sun


  Access Paper or Ask Questions

FedKD: Communication Efficient Federated Learning via Knowledge Distillation


Aug 30, 2021
Chuhan Wu, Fangzhao Wu, Ruixuan Liu, Lingjuan Lyu, Yongfeng Huang, Xing Xie


  Access Paper or Ask Questions

Beyond Model Extraction: Imitation Attack for Black-Box NLP APIs


Aug 29, 2021
Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari


  Access Paper or Ask Questions

A Novel Attribute Reconstruction Attack in Federated Learning


Aug 16, 2021
Lingjuan Lyu, Chen Chen

* accepted by FTL-IJCAI'21 Oral 

  Access Paper or Ask Questions

A Vertical Federated Learning Framework for Graph Convolutional Network


Jun 22, 2021
Xiang Ni, Xiaolong Xu, Lingjuan Lyu, Changhua Meng, Weiqiang Wang


  Access Paper or Ask Questions

Killing Two Birds with One Stone: Stealing Model and Inferring Attribute from BERT-based APIs


May 23, 2021
Lingjuan Lyu, Xuanli He, Fangzhao Wu, Lichao Sun

* paper under review 

  Access Paper or Ask Questions

Robust Training Using Natural Transformation


May 10, 2021
Shuo Wang, Lingjuan Lyu, Surya Nepal, Carsten Rudolph, Marthie Grobler, Kristen Moore

* arXiv admin note: text overlap with arXiv:1912.03192, arXiv:2004.02546 by other authors 

  Access Paper or Ask Questions

Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!


Mar 18, 2021
Xuanli He, Lingjuan Lyu, Qiongkai Xu, Lichao Sun

* accepted to NAACL2021 

  Access Paper or Ask Questions

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks


Jan 27, 2021
Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma

* 19 pages, 14 figures, ICLR 2021 

  Access Paper or Ask Questions

Privacy and Robustness in Federated Learning: Attacks and Defenses


Dec 07, 2020
Lingjuan Lyu, Han Yu, Xingjun Ma, Lichao Sun, Jun Zhao, Qiang Yang, Philip S. Yu

* arXiv admin note: text overlap with arXiv:2003.02133; text overlap with arXiv:1911.11815 by other authors 

  Access Paper or Ask Questions

Towards Building a Robust and Fair Federated Learning System


Nov 20, 2020
Xinyi Xu, Lingjuan Lyu

* In submission, under review 

  Access Paper or Ask Questions

Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness


Oct 03, 2020
Lingjuan Lyu, Xuanli He, Yitong Li

* accepted to Findings of EMNLP 2020 

  Access Paper or Ask Questions

Federated Model Distillation with Noise-Free Differential Privacy


Sep 11, 2020
Lichao Sun, Lingjuan Lyu

* under submission 

  Access Paper or Ask Questions

Collaborative Fairness in Federated Learning


Aug 28, 2020
Lingjuan Lyu, Xinyi Xu, Qian Wang

* accepted to FL-IJCAI'20 workshop 

  Access Paper or Ask Questions

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning


Jul 18, 2020
Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu, Xingjun Ma

* Accepted for publication in TDSC 

  Access Paper or Ask Questions

Towards Differentially Private Text Representations


Jun 25, 2020
Lingjuan Lyu, Yitong Li, Xuanli He, Tong Xiao

* Accepted to SIGIR'20 

  Access Paper or Ask Questions

Local Differential Privacy based Federated Learning for Internet of Things


Apr 19, 2020
Yang Zhao, Jun Zhao, Mengmeng Yang, Teng Wang, Ning Wang, Lingjuan Lyu, Dusit Niyato, Kwok Yan Lam


  Access Paper or Ask Questions

Threats to Federated Learning: A Survey


Mar 04, 2020
Lingjuan Lyu, Han Yu, Qiang Yang

* 7 pages, 4 figures, 2 tables 

  Access Paper or Ask Questions

Towards Fair and Decentralized Privacy-Preserving Deep Learning with Blockchain


Jun 04, 2019
Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin

* 13 pages, 5 figures, 6 tables 

  Access Paper or Ask Questions