Research

Thank you for your interest in my research works. I’m always happy to discuss them with you.

Research Interest

  1. Cybersecurity risks of Large Language Models (LLMs)
  2. Opportunities of adopting LLMs in security
  3. Trusted Execution Environments on multi-core devices

Publication

  1. Chennabasappa, C., Nikolaidis, C., Song, D., Molnar, D., Ding, S., Wan, S., Whitman, S., Deason, L., Doucette, N., Montilla, A., Gampa, A., Paola, B., Gabi, D., Crnkovich, J., Testud, J., He, K., Chaturvedi, R., Zhou, W., Saxe, J. “LlamaFirewall: An open source guardrail system for building secure AI agents”. arXiv, 2025. [paper, GitHub]
  2. Wan, S., Nikolaidis, C., Song, D., Molnar, D., Crnkovich, J., Grace, J., Bhatt, M., Chennabasappa, S., Whitman, S., Ding, S., Ionescu, V., Li, Y., Saxe, J. “CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models”. arXiv, 2024. [paper, GitHub]
  3. Llama Team, AI @ Meta (Wan, S. as one of core contributors). “The Llama 3 Herd of Models”. arXiv, 2024. [paper]
  4. Wan, S., Saxe, J., Gomes, C., Chennabasappa, S., Rath, A. , Sun, K., Wang, X. “Bridging the Gap: A Study of AI-based Vulnerability Management between Industry and Academia”. In proceedings of IEEE/IFIP DSN 2024, Industry Track. [paper]
  5. Meta GenAI Cybersec Team (Wan, S. as one of co-equal primary authors). “CYBERSECEVAL 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models”. arXiv, 2024. [paper]
  6. Meta GenAI Cybersec Team (Wan, S. as one of co-equal primary authors). “Purple Llama CyberSecEval: A benchmark for evaluating the cybersecurity risks of large language models”. arXiv, 2023. [paper]
  7. Wang, J., Sun, K., Lei, L., Wang, Y., Jing, J., Wan, S., Li, Q.. “CacheIEE: Cache-assisted Isolated Execution Environment on ARM Multi-Core Platforms”. IEEE Transactions on Dependable and Secure Computing, 2023.
  8. Xing, Y., Cao, J., Sun, K., Yan, F., Wan, S.. “The devil is in the detail: Generating system call whitelist for Linux seccomp”. Future Generation Computer Systems 135, 105-113, 2022. 1.Wan, S., Sun, K., Zhang, N., Li, Y. “Remotely Controlling TrustZone Applications? A Study on Securely and Resiliently Receiving Remote Commands”. In proceedings of ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec) 2021. [slides]
  9. Wan, S., Sun, M., Sun, K., Zhang, N., He, X. “RusTEE: Developing Memory-Safe ARM TrustZone Applications”. In proceedings of Annual Computer Security Applications Conference (ACSAC) 2020. [slides, GitHub] 2.Wang, J., Sun, K., Lei, L., Wan, S., Wang, Y., Jing, J. “Cache-in-the-Middle (CITM) Attacks : Manipulating Sensitive Data in Isolated Execution Environments”. In proceedings of ACM Conference on Computer and Communications Security (CCS) 2020.
  10. Wan, S., Sun, J., Sun, K., Zhang, N., Li, Q. “SATIN: A Secure and Trustworthy Asynchronous Introspection on Multi-Core ARM Processors”. In proceedings of IEEE/IFIP DSN 2019. Received DSN 2019 Student Travel Award. [slides]
  11. Wan, S., Li, Y., and Sun, K. “PathMarker: Protecting Web Contents against Inside Crawlers”. Cybersecurity, 2(1), 2019.
  12. Wan, S., Li, Y., and Sun, K. “Protecting Web Contents against Persistent Distributed Crawlers”. In Proceedings of IEEE ICC 2017. [slides]

Service

  • Journal reviewer: IEEE Transactions on Information Forensics and Security, IEEE/ACM Transactions on Networking, IEEE Internet Computing, ACM Digital Threats: Research and Practice, CCF Transactions on Networking.
  • Conference reviewer: IEEE INFOCOM 2020, IEEE ICC 2019, IEEE CNS 2018/2016.
  • Conference sub-reviewer: ICICS 2020/2019/2018, ICDCS 2020/2019, Securecomm 2018/2017, SciSec 2018.

Last updated: May, 2025