Yanyun Wang

Research Assistant

The Hong Kong Polytechnic University

Biography

Currently, I am a full-time research assistant at Applied Security, Trust And Privacy Lab for Enterprise, The Hong Kong Polytechnic University under the supervision of Prof. Haibo Hu. During the last three years, I also worked as a part-time research assistant at Shanghai Key Laboratory of Trustworthy Computing under the supervision of Prof. Dehui Du.

Interests

Adversarial Attack
Robust Machine Learning
Trustworthy AI

Education

M.Sc. in Computer Science, 2022-2023
The University of Hong Kong
Summer Student in Computing, 2021
National University of Singapore
B.Eng. in Software Engineering, 2018-2022
East China Normal University

Publications

Yanyun Wang, Dehui Du, Haibo Hu, Yuanhao Liu (2023). TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Gray-Box Attack. ArXiv preprint.

Code

Yanyun Wang, Dehui Du, Yuanhao Liu (2023). Meta Pattern Concern Score: A Novel Evaluation Measure with Human Values for Multi-classifiers. In The IEEE International Conference on Systems, Man, and Cybernetics (SMC, CCF-C). Accepted to appear.

Mingjun Ma, Dehui Du, Yuanhao Liu, Yanyun Wang, Yiyang Li (2022). Efficient Adversarial Sequence Generation for RNN with Symbolic Weighted Finite Automata. In Safe AI Workshop @ The AAAI Conference on Artificial Intelligence (AAAI, CCF-A). Best Paper Award Nomination.

PDF Cite Slides Video

Blogs

Reading Note of the Paper "Membership Inference Attacks on Machine Learning - A Survey"

Membership Inference Attack (MIA) is to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach.

Yanyun Wang

Last updated on Jun 17, 2023 1 min read

Reading Note of the Paper "Membership Inference Attacks on Machine Learning - A Survey"

Reading Note of the Paper "Survey - Leakage and Privacy at Inference Time"

Leakage of data from publicly available ML models is an area of growing significance since it can draw on multiple sources of data, including users’ sensitive data.

Yanyun Wang

Last updated on Jul 1, 2023 1 min read

Reading Note of the Paper "Survey - Leakage and Privacy at Inference Time"

Reading Note of the Paper "Threats to Pre-trained Language Models - Survey and Taxonomy"

Pre-trained language models (PTLMs) have achieved great success and remarkable performance, while there are growing concerns regarding their security issues.

Yanyun Wang

Last updated on Jul 10, 2023 1 min read

Reading Note of the Paper "Threats to Pre-trained Language Models - Survey and Taxonomy"

Honors & Awards

- Excellent Graduate Award, East China Normal University, 2022
- Excellent Bachelor's Degree Thesis Award, East China Normal University, 2022
- Excellent Undergraduate Student, East China Normal University, 2020 & 2021
- First / Second-class Scholarship, East China Normal University, 2020 / 2021