139 citations · 492 across the 39 of their papers we have counts for
7 papers · 1 filter
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
Xuanli He, Qiongkai Xu, Lingjuan Lyu +2
Nowadays, due to the breakthrough in natural language generation (NLG), including machine translation, document summarization, image captioning, etc NLG models have been encapsulat…
Bulk carrier lifetime surpassing 600 us in Upgraded Metallurgical-grade Silicon multicrystalline wafers after Phosphorus Diffusion Gettering
Nerea Dasilva-Villanueva, Sergio Catalán-Gómez, David Fuertes Marrón +2
Upgraded metallurgical-grade (UMG) Si is obtained via a purification route alternative to the one used for conventional polysilicon and with significantly reduced environmental imp…
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…
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
Qiongkai Xu, Xuanli He, Lingjuan Lyu +2
Machine-learning-as-a-service (MLaaS) has attracted millions of users to their splendid large-scale models. Although published as black-box APIs, the valuable models behind these s…
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…
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…
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…