Tu Ouyang

Orcid: 0000-0002-5432-5391

According to our database1, Tu Ouyang authored at least 10 papers between 2009 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning.
CoRR, March, 2026

EASE: Practical and Efficient Safety Alignment for Small Language Models.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation.
Proc. Priv. Enhancing Technol., 2025

Navigating the Designs of Privacy-Preserving Fine-tuning for Large Language Models.
Proceedings of the Companion Proceedings of the ACM on Web Conference 2025, 2025

Poster: Measuring Algorithmic Systems' Resilience Against Generative AI-Powered Attacks - Case Study on Exploiting a Code Search Platform.
Proceedings of the 2025 ACM Internet Measurement Conference, 2025

2024
Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks.
Proceedings of the 9th IEEE European Symposium on Security and Privacy, 2024

2022
Lifting Existing Applications to the Cloud: Abstractions, Separation of Responsibilities and Tooling Support.
Proceedings of the 24th International Conference on Enterprise Information Systems, 2022

2014
A large-scale empirical analysis of email spam detection through network characteristics in a stand-alone enterprise.
Comput. Networks, 2014

2011
Can Network Characteristics Detect Spam Effectively in a Stand-Alone Enterprise?
Proceedings of the Passive and Active Measurement - 12th International Conference, 2011

2009
Dynamic TCP Proxies: Coping with Disadvantaged Hosts in MANETs.
Proceedings of the 29th IEEE International Conference on Distributed Computing Systems Workshops (ICDCS 2009 Workshops), 2009


  Loading...