Dr Yujin Huang
Lecturer
School of Computer Science and Information Technology
College of Engineering and Information Technology
I’m an Assistant Professor at the School of Computer Science and Information Technology, Adelaide University. I’m also an Honorary Fellow at The University of Melbourne, where I obtained my PhD.
My research interests lie in Trustworthy On-device AI Systems, specifically focusing on three directions:
(1) Mobile AI System Security: Characterizing deployed AI system security, such as adversarial vulnerabilities, model tampering, and model protection.
(2) Post-Deployment Model Safety: Assessing model safety after deployment, such as guardrail bypasses and training-free backdoor attacks.
(3) Embodied AI System Security: Exploring security challenges in embodied AI systems, such as robustness, resilience, and secure interaction.
My research has been incorporated into influential AI safety research and policy materials from Meta’s Llama 2, Google DeepMind’s STAR, Monetary Authority of Singapore’s Emerging Risks and Opportunities of Generative AI for Banks, Center for Democracy & Technology’s Comments to NTIA on Open Foundation Models, and Council of the European Union’s ChatGPT in the Public Sector – overhyped or overlooked?.
I am always looking for self-motivated PhD students to join my group, and interested applicants are encouraged to email me at yujin.huang@adelaide.edu.au with your CV. I also welcome research assistants, master students, and undergraduate students who are interested in working with me on ongoing research projects.
| Date | Position | Institution name |
|---|---|---|
| 2026 - ongoing | Assistant Professor | Adelaide University |
| Year | Citation |
|---|---|
| 2026 | Zhuo, T. Y., Huang, Y., Chen, C., Du, X., & Xing, Z. (2026). Bypassing Guardrails: Lessons Learned from Red Teaming ChatGPT. ACM Transactions on Software Engineering and Methodology, 35(5), 1-21. Scopus1 |
| 2026 | Huang, Y., Yuan, X., Chen, C., & Hwang, S. O. (2026). Typhon Unleashed: Practical Adversarial Weight Attacks Against On-Device Deep Learning Models. IEEE Transactions on Dependable and Secure Computing, 23(3), 6584-6601. |
| 2024 | Ke, F., Wang, W., Tan, W., Du, L., Jin, Y., Huang, Y., & Yin, H. (2024). HiTSKT: A hierarchical transformer model for session-aware knowledge tracing. Knowledge Based Systems, 284, 13 pages. Scopus67 WoS48 |
| 2023 | Hu, H., Huang, Y., Chen, Q., Zhuo, T. Y., & Chen, C. (2023). A First Look at On-device Models in iOS Apps. ACM Transactions on Software Engineering and Methodology, 33(1), 30 pages. Scopus11 WoS5 |
| 2022 | Huang, Y., & Chen, C. (2022). Smart App Attack: Hacking Deep Learning Models in Android Apps. IEEE Transactions on Information Forensics and Security, 17, 1827-1840. Scopus28 WoS21 |
| Year | Citation |
|---|---|
| 2026 | Liu, Y., Ning, J., Feng, Q., Zhang, Y., Huang, Y., & Zhang, L. Y. (2026). GRASP: Hard-Label Black-Box Malware Evasion with Higher Success, Fewer Queries, and Smaller Perturbations. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (pp. 4590-4598). International Joint Conferences on Artificial Intelligence Organization. DOI |
| 2026 | Chang, S., Huang, H., Zhang, Y., Huang, Y., Xiao, F., & Zhang, L. Y. (2026). Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation. In Proceedings of the Aaai Conference on Artificial Intelligence Vol. 40 (pp. 57-65). Association for the Advancement of Artificial Intelligence (AAAI). DOI |
| 2025 | Wang, Z., Song, Y., Qin, S., Yu, S., Huang, Y., Xuan, Q., & Zheng, X. (2025). Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions. In Advances in Neural Information Processing Systems Vol. 38 (pp. 155366-155390). Neural Information Processing Systems Foundation, Inc. (NeurIPS). DOI Scopus1 |
| 2025 | Huang, Y., Zhang, Z., Zhao, Q., Yuan, X., & Chen, C. (2025). THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models. In Proceedings of the 34th Usenix Security Symposium (pp. 7311-7330). Scopus10 |
| 2024 | Hua, Y., Huang, Y., Huang, S., Feng, T., Qu, L., Bain, C., . . . Haf, R. (2024). Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction. In Proceedings of the 2024 Findings of the Association for Computational Linguistics (EMNLP) (pp. 8139-8156). Miami, USA: Association for Computational Linguistics. DOI Scopus5 |
| 2023 | Wang, Z., Huang, S., Huang, Y., & Cui, H. (2023). Energy-Latency Attacks to On-Device Neural Networks via Sponge Poisoning. In ACM International Conference Proceeding Series (pp. 11 pages). AUSTRALIA, Melbourne: ASSOC COMPUTING MACHINERY. DOI Scopus1 WoS3 |
| 2023 | Huang, Y., Zhuo, T. Y., Xu, Q., Hu, H., Yuan, X., & Chen, C. (2023). Training-free Lexical Backdoor Attacks on Language Models. In ACM Web Conference 2023 Proceedings of the World Wide Web Conference Www 2023 (pp. 2198-2208). ACM. DOI Scopus43 |
| 2023 | Sang, Y., Huang, Y., Huang, S., & Cui, H. (2023). Beyond the Model: Data Pre-processing Attack to Deep Learning Models in Android Apps. In ACM International Conference Proceeding Series (pp. 9 pages). AUSTRALIA, Melbourne: ASSOC COMPUTING MACHINERY. DOI Scopus1 |
| 2023 | Zhuo, T. Y., Li, Z., Huang, Y., Shiri, F., Wang, W., Haffari, G., & Li, Y. F. (2023). On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex. In A. Vlachos, & I. Augenstein (Eds.), Eacl 2023 17th Conference of the European Chapter of the Association for Computational Linguistics Proceedings of the Conference (pp. 1090-1102). CROATIA, Dubrovnik: ASSOC COMPUTATIONAL LINGUISTICS-ACL. DOI Scopus37 WoS28 |
| 2023 | Hu, H., Zhan, H., Huang, Y., & Liu, D. (2023). Pairwise GUI Dataset Construction Between Android Phones and Tablets. In Advances in Neural Information Processing Systems Vol. 36 (pp. 59860-59872). Neural Information Processing Systems Foundation, Inc. (NeurIPS). DOI Scopus5 |
| 2021 | Huang, Y., Hu, H., & Chen, C. (2021). Robustness of on-Device Models: Adversarial Attack to Deep Learning Models on Android Apps. In Proceedings International Conference on Software Engineering (pp. 101-110). ELECTR NETWORK: IEEE COMPUTER SOC. DOI Scopus42 WoS36 |
