王雯婕

• 深度学习，隐私计算，对抗机器学习，机器学习安全算法，联邦学习，自然语言处理

王雯婕博士现为上海科技大学信息科技与技术学院的助理教授、研究员、博士生导师。2017在华中科技大学获得学士学位，2022在美国埃默里大学计算机科学系获得博士学位。主要研究领域是人工智能的隐私性和安全性，尤其是在自然语言处理和医疗领域的相关应用，包括联邦学习、差分隐私、对抗样本和可验证鲁棒性。

1. “Certified Robustness to Word Substitution Attack with Differential Privacy”, Wenjie Wang, Pengfei Tang, Jian Lou, Li Xiong, North American Chapter of the Association for Computational Linguistics (NAACL) 2021

2. “Generating Adversarial Examples with Distance Constrained Adversarial Imitation Networks”, Pengfei Tang, Wenjie Wang, Li Xiong, IEEE Transactions on Dependable and Secure Computing (TDSC) 2021

3. “RADAR: Recurrent Autoencoder based Detector for Adversarial Temporal EHR”, Wenjie Wang, Pengfei Tang，Li Xiong, Xiaoqian Jiang, The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML)2020 （电子医疗数据的对抗样本防御算法）

4. “Utilizing Multimodal Model Consistency to Detect Adversarial Examples”, Wenjie Wang, Youngja Park, Taesung Lee, Ian Molloy, Pengfei Tang, Li Xiong, Empirical Methods in Natural Language Processing(EMNLP)workshop: ClinicalNLP2020

5. “Efficient Text Analysis with Pre-trained Neural Network Models”, Jia Cui, Heng Lu, Wenjie Wang, Shiyin Kang, Liqiang He, Guangzhi Li, Dong Yu, IEEE Spoken Language Technology Workshop (SLT) 2022