Avatar
Tiansheng Huang
PhD candidate at Georgia Institute of Technology
  • Email: tianshenghuangscut at gmail.com

Biography

I am a fifth-year CS PhD student at Georgia Institute of Technology, Atlanta, USA, advised by Prof. Ling Liu and Prof. Santosh Pande. Prior to that, I received my B.E./master degree from South China University of Technology, Guangzhou, China, advised by Prof. Weiwei Lin. My research interests mainly focus on post-training methods (e.g., safety post-training, multi-modal alignment, agentic post-training). My PhD thesis is fortunately to be supported by Google PhD fellowship 2025.

My PhD thesis research focuses on enhancing large language model (LLM) safety via designing new post-training algorithms/data synthetic pipeline. Particularly, I am working on tackling harmful fine-tuning, the most effective data poisoning-based attack to destroy the safety alignment of a LLM.

Relevant research papers I did during my PhD include:

I am now on the job market and am open to opportunities on multimodal LLM post-training (e.g., safety post-training, multi-modal alignment, agentic post-training, etc) or data synthetic. Thanks for the recommendation.

Publications

  • T. Huang, G. Bhattacharya, P. Joshi, J. Kimball, L. Liu, “Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning,” ICML2025 [arXiv] [homepage] [code]
  • T. Huang, S. Hu, F. Ilhan, S. Tekin, L. Liu, “Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation,” ICLR2025 (Oral) [arXiv] [homepage] [code]
  • T. Huang, S. Hu, L. Liu, “Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning,” NeurIPS2024 [arXiv] [homepage] [code]
  • T. Huang, S. Hu, F. Ilhan, S. Tekin, L. Liu, “Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning,” NeurIPS2024 [arXiv] [code]
  • T. Huang, S. Hu, KH. Chow, F. Ilhan, S. Tekin, L. Liu, “Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training,” NeurIPS2023.[Paper] [Code]
  • T. Huang, S. Hu, F. Ilhan, S. Tekin, L. Liu, “Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey,” ACM Computing Surveys (CSUR) [arXiv] [Paper list (continuously update)] [slide]
  • T. Huang, L. Shen, Y. Sun, W. Lin, and D. Tao, “Fusion of Global and Local Knowledge for Personalized Federated Learning,” 2023, Transactions on Machine Learning Research (TMLR). [OpenReview] [Code]
  • T. Huang, W. Lin, L. Shen, K. Li and A. Y. Zomaya, “Stochastic Client Selection for Federated Learning with Volatile Clients,” 2022, IEEE Internet of Things Journals (IOT-J). [arXiv]
  • T. Huang, W. Lin, X. Hong , X. Wang, Q. Wu, R. Li, CH. Hsu, AY. Zomaya, “Adaptive Processor Frequency Adjustment for Mobile Edge Computing with Intermittent Energy Supply”, 2021, IEEE Internet of Things Journals (IOT-J). [arXiv] [code]
  • T. Huang, W. Lin, W. Wu, L. He, K. Li and AY. Zomaya, “An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guarantee,” 2020, IEEE Transactions on Parallel and Distributed Systems (TPDS) (Special Section on Parallel and Distributed Computing Techniques for AI, ML, and DL). [arXiv]
  • T. Huang, W. Lin, C. Xiong, R. Pan and J. Huang, “An Ant Colony Optimization Based Multi-objective Service Replicas Placement Strategy for Fog Computing,” 2020, IEEE Transactions on Cybernetics (TCYB).
  • Z Yahn, SF Tekin, F Ilhan, S Hu, T Huang, Y Xu, M Loper, L Liu, “Adversarial Attention Perturbations for Large Object Detection Transformers,” ICCV2025 [arXiv] [code]
  • S. Tekin, F. Ilhan, T. Huang, S. Hu, L. Liu, “LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity,” EMNLP 2024 (Findings) [Paper] [code]
  • K. Chow, S. Hu, T. Huang, L. Liu, “Personalized Privacy Protection Mask Against Unauthorized Facial Recognition”, ECCV2024. [Paper]
  • K. Chow, S. Hu, T. Huang, F. Ilhan, W. Wei, L. Liu, “Diversity-driven Privacy Protection Masks Against Unauthorized Face Recognition”, PET2024. [Paper]
  • F. Ilhan, G. Su, S. Tekin, T. Huang, S. Hu, L. Liu, “Resource-Efficient Transformer Pruning for Finetuning of Large Models”, CVPR2024. [Paper]
  • S.Hu, T. Huang, KH. Chow, W. Wei, Y. Wu, L. Liu. “ZipZap: Efficient Training of Language Models for Ethereum Fraud Detection”, WWW2024. [Paper]
  • F. Ilhan, KH. Chow, S. Hu, T. Huang, S. Tekin, W. Wei, Y. Wu, M. Lee, R.Kompella, H. Latapie, G. Liu, L. Liu, “Adaptive Deep Neural Network Inference Optimization with EENet,” WACV2024 [Paper]
  • S.Hu, T. Huang, F. Ilhan, S. Tekin, L. Liu. “Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives”, TPS2023. [Paper]
  • F. Ilhan, S. Tekin, S. Hu, T. Huang, KH. Chow, L. Liu, “Hierarchical Deep Neural Network Inference for Device-Edge-Cloud Systems,” WWW2023 (short paper).[Paper]
  • Y. Sun, L. Shen, T. Huang, and D. Tao, “FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy”, ICLR2023. [OpenReview]

Preprint&OpenReview

  • T. Huang, S. Liu, L. Shen, F. He, W. Lin, D. Tao, “Achieving Personalized Federated Learning with Sparse Local Models,” preprint [arXiv]
  • T. Huang, S. Hu, F. Ilhan, S. Tekin, L. Liu, “Virus: Harmful Fine-tuning Attack for Large Language Models bypassing Guardrail Moderation,” preprint [arXiv] [code]
  • T. Huang, S. Hu, F. Ilhan, S. Tekin, Z. Yahn, Y.Xu, L. Liu, “Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable,” preprint [arXiv] [code]

Industrial Experience

Student research at Google DeepMind, Atlanta, USA, with Virat Shejwalker, Oscar Chang. (August. 2025 ~ Nov. 2025)

  • Alignment stage defense against harmful fine-tuning.

Research intern at Google DeepMind, Mountain view, USA, with Virat Shejwalker, Oscar Chang, Milad Nasr. (May. 2025 ~ August. 2025)

  • Safety alignment for large audio reasoning models against audio jailbreak attack.

Research intern at Dolby Laboratories, Atlanta, USA, with Gautam Bhattacharya, Pratik Joshi and Josh Kimball. (May. 2024 ~ August. 2024)

  • Post-fine-tuning stage defense aginst harmful fine-tuning for LLMs.

Research intern at JD explore academy, Beijing, China, with Li Shen. (March. 2022 ~ June. 2022)

  • Low-rank+sparse compression for personalized federated learning.
  • Application of proximal algorithms.

Research intern at JD explore academy, Beijing, China, with Li Shen. (Jun. 2021 ~ Oct. 2021)

  • Develop high-efficiency model compression algorithm for distributed ML.
  • Optimization for Personalized Federated Learning.

Awards & Honors

  • Google PhD fellowship, 2025
  • Outstanding reviewer of ICLR'24
  • Top reviewer of NeurIPS'23
  • Student Travel Grants of IEEE TPS, 2023
  • National Scholarship for Graduate, 2021
  • National Scholarship for Graduate, 2020
  • The First-Class School Scholarship, 2019

Services

  • Conference Reviewer: NeurIPS (‘23,‘24,‘25), ICLR (‘24,‘25, ‘26, ‘27), ICML (‘24,‘25,‘26), AAAI'25, AISTATS'25, AAAI'25-AIA, ACL-ARR, CVPR'25.
  • Journal Reviewer: IEEE TMC, IEEE TCOM, IEEE TP, ACM TOIT, TMLR, IEEE TIFS, IEEE TBD, TPAMI.