Research Output

Publications

AI for Security

1

Identifying Non-Control Security-Critical Data in Program Binaries with a Deep Neural Model

Zhilong Wang*, Haizhou Wang*, Hong Hu, and Peng Liu (* co-first author)

Transactions on Dependable and Secure Computing (TDSC), 2025

PDF
2025
2

DeepSanitizer: Combining Heuristic Rules and Deep Learning Models to Spot Silent Buffer Overflows in Binary

Zhilong Wang, Chen Cao, Yu Li, Suhang Wang, Xiaoyan Sun, Peng Liu

Transactions on Dependable and Secure Computing (TDSC), 2025

PDF
2025
3

Deep Learning Assisted Reverse Engineering: Recognizing Encryption Loops in Ransomware

Nanqing Luo*, Haizhou Wang*, Zhilong Wang*, Lan Zhang, Ping Chen, Peng Liu (* co-first author)

TrustCom 2025

PDF
2025
4

DESCG: Data Encoding Scheme Classification with GNN in Binary Analysis

Xushu Dai, Nanqing Luo, Haizhou Wang, Zhilong Wang, Chen Cao, Peng Liu

Automated Software Engineering (ASE), Springer 2025

2025
5

How Does Naming Affect Language Models on Code Analysis Tasks?

Zhilong Wang, Lan Zhang, Chen Cao, Nanqing Luo, Xinzhi Luo, and Peng Liu

Journal of Software Engineering and Applications, 2024

2024
6

Using Deep Learning to Solve Computer Security Challenges: A Survey

Yoon-Ho Choi, Peng Liu, Zitong Shang, Haizhou Wang, Zhilong Wang, Lan Zhang, Junwei Zhou and Qingtian Zou

Cybersecurity, 2020 (authors in alphabetical order)

PDF
2020

Security for AI

1

From Pixels to Prompts: A Systematic Study and Introduction to Image Prompt Injection Attacks

Neha Nagaraja, Lan Zhang, Zhilong Wang

AI Column of IEEE Computer, 2026

2026
2

Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Carrier Articles

Zhilong Wang, Haizhou Wang, Nanqing Luo, Lan Zhang, Xiaoyan Sun, Yebo Cao, Peng Liu

EAI SecureComm, 2026

2026
3

Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions

Neha Nagaraja, Lan Zhang, Zhilong Wang, Bo Zhang, Pawan Patil

The 3rd International Conference on Foundation and Large Language Models (FLLM), 2025

2025
4

To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt

Zhilong Wang, Neha Nagaraja, Lan Zhang, Hayretdin Bahsi, Pawan Patil and Peng Liu

55th IEEE/IFIP DSN (Industry Track), 2025

PDF
2025

System and Software Security

1

GPT Conjecture: Understanding the Trade-offs between Granularity, Performance and Timeliness in Control-Flow Integrity

Zhilong Wang and Peng Liu

Cybersecurity, 2021

PDF
2021
2

HART: Hardware-assisted Kernel Module Tracing on Arm

Yunlan Du, Zhenyu Ning, Jun Xu, Zhilong Wang, Yueh-Hsun Lin, Fengwei Zhang, Xinyu Xing, and Bing Mao

25th European Symposium on Research in Computer Security (ESORICS), 2020

PDF
2020
3

To Detect Stack Buffer Overflow With Polymorphic Canaries

Zhilong Wang, Xuhua Ding, Chengbin Pang, Jian Guo, Jun Zhu and Bing Mao

IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2018

PDF
2018
4

DiffGuard: Obscuring Sensitive Information in Canary Based Protections

Jun Zhu, Weiping Zhou, Zhilong Wang, Dongliang Mu, and Bing Mao

International Conference on Security and Privacy in Communication Systems (SecureComm), 2017

PDF
2017
5

ROPOB: Obfuscating Binary Code via Return Oriented Programming

Dongliang Mu, Jia Guo, Wenbiao Ding, Zhilong Wang, Bing Mao, and Lei Shi

International Conference on Security and Privacy in Communication Systems (SecureComm), 2017

PDF
2017