3 papers
cs.MM2025
Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models
Chaoyi Zhu, Zaitang Li, Renyi Yang +4
Watermarking becomes one of the pivotal solutions to trace and verify the origin of synthetic images generated by artificial intelligence models, but it is not free of risks. Recen…
cs.AI2024
Retention Score: Quantifying Jailbreak Risks for Vision Language Models
Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho
The emergence of Vision-Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to enhance multi-modal machine learning…
cs.LG2024
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho
Current studies on adversarial robustness mainly focus on aggregating local robustness results from a set of data samples to evaluate and rank different models. However, the local…