Scholar
Yun-Yun Tsai
Google Scholar ID: v1SiKHcAAAAJ
Ph.D. student at Computer Science, Columbia University
Citations & Impact
Citations
689
H-index
8
i10-index
7
Publications
17
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- GDA: Generalized Diffusion for Robust Test-time Adaptation, CVPR 2024
- From Detection to Deception: Are AI-Generated Image Detectors Adversarially Robust?, CVPR 2024, Responsible Generative AI Workshop
- Towards Robust Detection of AI-Generated Videos, CVPR 2024, Generative Models for Computer Vision Workshop
- Convolutional Visual Prompt for Robust Visual Perception, NeurIPS 2023
- Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations, CVPR 2023
- Test-time Defense against Adversarial Attacks: Detection and Reconstruction of Adversarial Examples via Masked Autoencoder, CVPR 2023, AdvML Workshop
- CARBEN: Composite Adversarial Robustness Benchmark, IJCAI 2022
- Generalizing Adversarial Training to Composite Semantic Perturbations, ICML 2021, AdvML Workshop
- Voice2Series: Reprogramming Acoustic Models for Time Series Classification, ICML 2021
- Transfer Learning without Knowing, Reprogramming Black-box Machine Learning Model with Scarce Data and Limited Resources, ICML 2020
- CloudLeak: Large-Scale Deep Learning Models Stealing Through Adversarial Examples, NDSS 2020
Research Experience
- May 2024: Started as a research scientist intern at Meta GenAI Team in New York, NY.
- May 2023: Started as an applied scientist intern at Amazon Astro Team in Bellevue, Washington.
- April 2024: Passed her Ph.D. candidacy exam.
- February 2024: One main conference paper and two workshop papers accepted by CVPR 2024.
- September 2023: One paper accepted by NeurIPS 2023.
- March 2023: Two papers accepted by CVPR 2023.
Education
- Received M.S. and B.S. in computer science from National Tsing Hua University (NTHU), Taiwan. Previously, she was advised by Professor Tsung-Yi Ho and Dr. Pin-Yu Chen from IBM Research Trusted AI group.
Background
- A fourth-year Ph.D. candidate in the Department of Computer Science at Columbia University, advised by Professor Junfeng Yang. Her research interests focus on security in artificial intelligence, particularly in improving the trustworthy, security, and robustness of machine learning (ML) algorithms and computer systems.
