prof_pic.jpg

Room 3006

Cheng Yu Tung Building

Dongdong She

Assistant Professor
Department of Computer Science and Engineering
Hong Kong University of Science and Technology
dongdong@cse.ust.hk

Google Scholar, GitHub, Twitter

Drop me an email if you are interested in working with me!

I received my Ph.D. from the Department of Computer Science at Columbia University, working with Suman Jana and Baishakhi Ray. Before coming to Columbia, I worked with Zhiyun Qian on Android security at the University of California, Riverside. I earned my bachelor’s degree at Huazhong University of Science and Technology.

I am broadly interested in the intersection of security and machine learning. In particular, I focus on applying data-driven approaches (e.g., large language models, machine learning, and optimization) to solve security problems. My work has earned Distinguished Paper Awards at ASE, IEEE S&P, and ISSTA, the ACM CCS Best Paper Runner-Up Award, and finalist honors in the NYU CSAW Applied Research Competition. Current research projects include:

  • LLM Safety & Security: investigating LLM safety, the safety and security of LLM-based agentic systems, with a focus on harmful failure modes and adversarial threats in long-horizon agentic tasks.
  • LLM Cyber: exploring the capabilities of LLMs in autonomous cybersecurity tasks, including vulnerability discovery, PoC generation, and exploit generation.

I am fortunate to work with these talented students:

  • Yuchong Xie (2024-Fall PhD, BS, MS@SJTU, ex-SJTU 0ops team, intern: Kimi RL team, Qwen foundation model cyber team) co-advised with Prof. Shuai Wang
  • Shuangjie Yao (2024-Fall PhD, BS@SJTU, Zhiyuan College, visiting: Columbia University 2025/12-2026/08, intern: Tencent Hunyuan Team)
  • Zesen Liu (2025-Fall PhD, BS@Xidian U, intern: Tencent Hunyuan Team)
  • Kaikai Zhang (2025-Fall PhD, BS@SJTU, intern: Qwen foundation model cyber team)
  • Zhixiang Zhang (2026-Fall PhD, BS@Fudan U)
  • Zihan Zhang (2027-Fall PhD, BS@SUSTech)

Publications

2026

  1. NeurIPS WS
    Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification
    Shuangjie Yao, Nikolaus Holzer, Mark Paul Santolucito, Baishakhi Ray, Suman Jana, and  Dongdong She
    NeurIPS 2026 Workshop on AI for Verifiable Coding, 2026.
    PDF
  2. arXiv
    Cheap to Hypothesize, Costly to Verify: The Defense Surface of Agentic Vulnerability Discovery
    Kaikai Zhang, Zihan Zhang, Yuchong Xie, Zesen Liu, Shuangjie Yao, Zhixiang Zhang, and  Dongdong She
    arXiv preprint
    PDF
  3. arXiv
    Similarity Is Not Validity: Defending LLM Semantic Caches Against Poisoning
    Zihan Zhang, Shuangjie Yao, Zesen Liu, Zhixiang Zhang, Wai Ip Lai, Dung Hiu Hilton Yeung, Chun Kit Zhang, Fuchen Ma, Yuanyuan Yuan, Yu Jiang, and 1 more author
    arXiv preprint
    PDF Code
  4. arXiv
    Compositional Safety Failures in Harness Evolution: Identification and Runtime Monitoring
    Zhixiang Zhang, Zesen Liu, Wai Ip Lai, Hongxu Chen, and  Dongdong She
    arXiv preprint
    PDF
  5. arXiv
    Safe to Check, Unsafe to Use: Relinking at the Compression Boundary of LLM Agents
    Zesen Liu, Zihan Zhang, and  Dongdong She
    arXiv preprint
    PDF
  6. ISSTA
    Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment
    Yuchong Xie, Mingyu Luo, Zesen Liu, Zhixiang Zhang, Kaikai Zhang, Yu Liu, Zongjie Li, Ping Chen, Shuai Wang, and  Dongdong She
    ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2026)
    PDF Code
  7. ASE
    When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents
    Zesen Liu, Zhixiang Zhang, Yuchong Xie, and  Dongdong She
    IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)
    Distinguished Paper Award
    PDF Code
  8. ASE
    Verifier-in-the-Loop LLM Solving of Heap Constraints for Concolic Execution
    Shaoran Xia, Leyi Cheng, Caihua Dong,  Dongdong She, Bo Wang, Xin Peng, and Zhen Dong
    IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)
  9. arXiv
    When Alignment Isn’t Enough: Response-Path Attacks on LLM Agents
    Mingyu Luo, Zihan Zhang, Zesen Liu, Yuchong Xie, Zhixiang Zhang, Dung Hiu Hilton Yeung, Wai Ip Lai, Ping Chen, Ming Wen, and  Dongdong She
    arXiv preprint
    PDF
  10. ICML
    From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching
    Zhixiang Zhang, Zesen Liu, Yuchong Xie, Quanfeng Huang, and  Dongdong She
    International Conference on Machine Learning (ICML 2026)
    PDF Code
  11. OOPSLA
    RandSet: Randomized Corpus Reduction for Fuzzing Seed Scheduling
    Yuchong Xie, Kaikai Zhang, Yu Liu, Rundong Yang, Ping Chen, Shuai Wang, and  Dongdong She
    Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA 2026)
    PDF Code
  12. arXiv
    QueryIPI: Query-agnostic Indirect Prompt Injection on Coding Agents
    Yuchong Xie, Zesen Liu, Mingyu Luo, Zhixiang Zhang, Kaikai Zhang, Yuanyuan Yuan, Zongjie Li, Ping Chen, Shuai Wang, and  Dongdong She
    arXiv preprint
    PDF

2025

  1. ISSTA
    ZTaint-Havoc: From Havoc Mode to Zero-Execution Fuzzing-Driven Taint Inference
    Yuchong Xie, Wenhui Zhang, and  Dongdong She
    ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2025)
    PDF Code
  2. ISSTA
    RouthSearch: Inferring PID Parameter Specification for Flight Control Program by Coordinate Search
    Siao Wang, Zhen Dong, Hui Li, Liwei Shen, Xin Peng, and  Dongdong She
    ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2025)
    Distinguished Paper Award
    PDF Code
  3. IEEE S&P
    Empc: Effective Path Prioritization for Symbolic Execution with Path Cover
    Shuangjie Yao, and  Dongdong She
    IEEE Symposium on Security and Privacy (S&P 2025)
    Distinguished Paper Award
    PDF Code

2024

  1. CCS
    FOX: Coverage-guided Fuzzing as Online Stochastic Control
    Dongdong She*, Adam Storek*, Yuchong Xie, Seoyoung Kweon, Prashast Srivastava, and Suman Jana
    ACM SIGSAC Conference on Computer and Communications Security (CCS 2024)
    Second Place in SBFT 2024 Fuzzing Competition
    PDF Code

2023

  1. IEEE S&P
    Precise Detection of Kernel Data Races with Probabilistic Lockset Analysis
    Gabriel Ryan, Abhishek Shah,  Dongdong She, and Suman Jana
    IEEE Symposium on Security and Privacy (S&P 2023)
    PDF

2022

  1. IEEE S&P
    Effective Seed Scheduling for Fuzzing with Graph Centrality Analysis
    Dongdong She, Abhishek Shah, and Suman Jana
    IEEE Symposium on Security and Privacy (S&P 2022)
    PDF Code
  2. CCS
    MC2: Rigorous and Efficient Directed Greybox Fuzzing
    Abhishek Shah,  Dongdong She, Samanway Sadhu, Krish Singal, Peter Coffman, and Suman Jana
    ACM SIGSAC Conference on Computer and Communications Security (CCS 2022)
    Best Paper Award Runner-Up
    PDF Code
  3. FSE
    NeuDep: Neural Binary Memory Dependence Analysis
    Kexin Pei,  Dongdong She, Michael Wang, Scott Geng, Zhou Xuan, Yaniv David, Junfeng Yang, Suman Jana, and Baishakhi Ray
    ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE 2022)
    PDF Code

2021

  1. Security
    Fine Grained Dataflow Tracking with Proximal Gradients
    Gabriel Ryan, Abhishek Shah,  Dongdong She, Koustubha Bhat, and Suman Jana
    USENIX Security Symposium (Security 2021)
    PDF

2020

  1. Security
    On Training Robust PDF Malware Classifiers
    Yizheng Chen, Shiqi Wang,  Dongdong She, and Suman Jana
    USENIX Security Symposium (Security 2020)
    PDF Code
  2. FSE
    MTFuzz: Fuzzing with a Multi-Task Neural Network
    Dongdong She, Rahul Krishna, Lu Yan, Suman Jana, and Baishakhi Ray
    ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (FSE 2020)
    PDF Code
  3. IEEE S&P
    Neutaint: Efficient Dynamic Taint Analysis with Neural Networks
    Dongdong She, Yizheng Chen, Abhishek Shah, Baishakhi Ray, and Suman Jana
    IEEE Symposium on Security and Privacy (S&P 2020)
    PDF

2019

  1. IEEE S&P
    NEUZZ: Efficient Fuzzing with Neural Program Smoothing
    Dongdong She, Kexin Pei, Dave Epstein, Junfeng Yang, Baishakhi Ray, and Suman Jana
    IEEE Symposium on Security and Privacy (S&P 2019)
    Finalist in 2019 NYU CSAW Applied Research Competition
    PDF Code

2016

  1. CCS
    Android ION Hazard: The Curse of Customizable Memory Management System
    Hang Zhang,  Dongdong She, and Zhiyun Qian
    ACM SIGSAC Conference on Computer and Communications Security (CCS 2016)
    PDF

2015

  1. CCS
    Android Root and Its Providers: A Double-Edged Sword
    Hang Zhang,  Dongdong She, and Zhiyun Qian
    ACM SIGSAC Conference on Computer and Communications Security (CCS 2015)
    PDF