activity
20192022
most citedNeural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

139 citations · 302 across the 13 of their papers we have counts for

collaborators

10 papers

cs.CR202113 cited

A Novel Attribute Reconstruction Attack in Federated Learning

Lingjuan Lyu, Chen Chen

Federated learning (FL) emerged as a promising learning paradigm to enable a multitude of participants to construct a joint ML model without exposing their private training data. E…

cs.CV2021

Robust Training Using Natural Transformation

Shuo Wang, Lingjuan Lyu, Surya Nepal +3

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations th…

cs.CL20216 cited

Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!

Xuanli He, Lingjuan Lyu, Qiongkai Xu +1

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows…

cs.LG2021139 cited

Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks

Yige Li, Xixiang Lyu, Nodens Koren +3

Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to contro…

cs.CR20203 cited

A Fast and Scalable Authentication Scheme in IoT for Smart Living

Jianhua Li, Jiong Jin, Lingjuan Lyu +4

Numerous resource-limited smart objects (SOs) such as sensors and actuators have been widely deployed in smart environments, opening new attack surfaces to intruders. The severe se…

cs.LG20206 cited

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

Lingjuan Lyu, Xuanli He, Yitong Li

It has been demonstrated that hidden representation learned by a deep model can encode private information of the input, hence can be exploited to recover such information with rea…