Zhejiang University:Master's (transferred to PhD in the spring semester)
September, 2019 - June, 2021
Cyberspace Security, College of Computer Science
Supervisor: Kui Ren, Zhan Qin
Awards:
ZJU Outstanding Graduate Student (2019)
Beijing University of Posts and Telecommunications:Bachelor degree
September, 2015 - June, 2019
Information Security, School of Cyberspace Security
Awards:
Beijing Outstanding Graduation Design (2019)First prize in National College Student Information Security Contest (2018)National Scholarship (2018)Rui'an Tech Scholarship (2017)
Internships
Tencent: Intelligent Security Research Group, Xuanwu Lab
March, 2021 - August, 2021
Outcomes:
BrutePrint: Expose Smartphone Fingerprint Authentication to Brute-force Attack PDF Issues
Professional Services
IEEE Transactions on Dependable and Secure Computing (TDSC):Reviewer
The framework to fine-tune existing malware/vulnerability classifiers with explanations and generate component-based explanations with feature attribution XAI methods, improving explanation fidelity and intelligibility. Refer to our CCS 2023 paper for more details.
tensorflowlimeshap
My Related Blogs:
LIME & SHAP ToolkitGradientExplainer
Represent android malware with a set of graphs, classify them with GNN, and explain the decisions with techniques including GNN-Explainer. Refer to our TDSC 2023 paper for more details.
pytorchpytorch-geometric
My Related Blogs:
GNN BasisPyG DatasetGNNExplainer
Download datasets from Androzoo, differentiate by year as well as benign/malicious applications. Supports coroutines, proxies, breakpoint continuation, error retries, etc.
pythonasyncio
This repo is no longer maintained but the Android malware feature extraction methods in related papers, i.e., Drebin, DAMD, MaMaDroid, Hindroid, and MsDroid, are ready to be used, which I re-implemented with androguard v3.4.
pythonandroguard
Credit to - base theme design: Tyler Butler, See it on
GitHub