...

Hi, Iā€™m Yiling He šŸ‘‹

  • šŸ”­ Iā€™m currently working on Code LLM applications, focusing on the problems of semantics preserving and robustness to drift
  • šŸŒ± Iā€™m always learning recent advances in the related domains and never limit myself to one way
  • šŸ‘Æ Iā€™m looking to collaborate on LLM-powered software security, e.g., for vulnerability detection, malware summary and defense
  • šŸ’¬ Visit my previous blog at https://e0hyl.github.io/BLOG-OF-E0
  • šŸ“« How to reach me: yiling-he@ucl.ac.uk (Research Fellow at University College London)

Contact Me

Selection of my recent publications here.

  1. Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
    Shuo Shao, Yiming Li, Hongwei Yao, Yiling He, Zhan Qin, and Kui Ren
    In Network and Distributed System Security Symposium (NDSS) 2025
  2. FINER: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis
    Yiling He, Jian Lou, Zhan Qin, and Kui Ren
    In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security (CCS) 2023
  3. DeUEDroid: Detecting Underground Economy Apps Based on UTG Similarity
    Zhuo Chen, Jie Liu, Yubo Hu, Lei Wu, Yajin Zhou, Yiling He, Xianhao Liao, Ke Wang, Jinku Li, and Zhan Qin
    In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) 2023
  4. MsDroid: Identifying Malicious Snippets for Android Malware Detection
    IEEE Transactions on Dependable and Secure Computing (TDSC) 2022

Experience including internships, services, education, and awards.

Education & Awards

University College London: Research Fellow

January, 2025 - now

S2Lab, Computer Science

Supervisor: Lorenzo Cavallaro

Zhejiang University: PhD degree

September, 2021 - June, 2024

Cyberspace Security, College of Computer Science

Supervisor: Kui Ren, Zhan Qin
Awards: ZJU Outstanding PhD Dissertation Funding Recipient (2023) ZJU Graduate Student of Five Merits (2022) ZJU Outstanding Graduate Student (2021~2022) Higgs University Student Extracurricular Innovation Scholarship (2021)

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

USENIX Security Symposium (USENIX Security): External Reviewer

2025

IEEE Symposium on Security and Privacy (IEEE S&P): External Reviewer

2025

ACM SIGSAC Conference on Computer and Communications Security (CCS): External Reviewer

2024, 2022

Tsinghua Science and Technology (TST): Reviewer

2025, 2024

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT): Reviewer

2024

IEEE Transactions on Dependable and Secure Computing (TDSC): Reviewer

2023

Selected projects from my Github, visit for more at https://github.com/E0HYL.

...
FINER-explain
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.
tensorflow lime shap My Related Blogs: LIME & SHAP Toolkit GradientExplainer
...
MsDroid
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.
pytorch pytorch-geometric My Related Blogs: GNN Basis PyG Dataset GNNExplainer
...
AndrozooDownloader
Download datasets from Androzoo, differentiate by year as well as benign/malicious applications. Supports coroutines, proxies, breakpoint continuation, error retries, etc.
python asyncio
...
AI4Code-Framework
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.
python androguard