Invited Talk
-
Towards Effective and Efficient Evaluation of Large Language Model’s Adversarial Robustness.
19 Apr 2024, *N-CRiPT Technical Workshop, NUS, Singapore.
[Slides] -
An LLM can Fool Itself: A Prompt-Based Adversarial Attack.
25 Mar 2024, N-CRiPT Seminar, NUS, Singapore.
[Slides] -
Towards Building Robust Foundation Models.
28 November 2023, N-CRiPT Seminar, NUS, Singapore.
[Slides] -
Towards Effective and Efficient Self-Supervised Robust Pre-training.
26 August 2023, 1st International Conference on AI-generated Content (AIGC 2023), Shanghai, China.
[Slides] [Certification]
Conference Presentation
- Adversarial Attack and Defense for Non-Parametric Two-Sample Tests.
21 July 2022, 39th International Conference on Machine Learning (ICML 2022), Baltimore, USA.
[Slides] [Poster]