activity
20142024
most citedFine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

41 citations · 81 across the 17 of their papers we have counts for

collaborators

17 papers

stat.ML2024

Uncertainty Quantification of Data Shapley via Statistical Inference

Mengmeng Wu, Zhihong Liu, Xiang Li +2

As data plays an increasingly pivotal role in decision-making, the emergence of data markets underscores the growing importance of data valuation. Within the machine learning lands…

cs.CY20244 cited

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

Yi Zeng, Kevin Klyman, Andy Zhou +6

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a sig…

cs.CR2024

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Yi Zeng, Weiyu Sun, Tran Ngoc Huynh +3

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionali…

cs.LG20241 cited

Fairness-Aware Meta-Learning via Nash Bargaining

Yi Zeng, Xuelin Yang, Li Chen +4

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation…

cs.CV2024

JIGMARK: A Black-Box Approach for Enhancing Image Watermarks against Diffusion Model Edits

Minzhou Pan, Yi Zeng, Xue Lin +4

In this study, we investigate the vulnerability of image watermarks to diffusion-model-based image editing, a challenge exacerbated by the computational cost of accessing gradient…

cs.LG20244 cited

Benchmarking Zero-Shot Robustness of Multimodal Foundation Models: A Pilot Study

Chenguang Wang, Ruoxi Jia, Xin Liu +1

Pre-training image representations from the raw text about images enables zero-shot vision transfer to downstream tasks. Through pre-training on millions of samples collected from…