Yuren Wu — accepted AI-conference papers

2024

LimeAttack: Local Explainable Method for Textual Hard-Label Adversarial Attack

Hai Zhu, Qingyang Zhao, Weiwei Shang, Yuren Wu, Kai Liu

AAAI 2024technical

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt model internal information (gradients or confidence scores) to generate adversarial examples. However, this information is unavailable in the real world. Therefore, we focus on a mo…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2021

Understanding Gradient Clipping In Incremental Gradient Methods

Jiang Qian, Yuren Wu, Bojin Zhuang, Shaojun Wang, Jing Xiao

AISTATS 2021poster

We provide a theoretical analysis on how gradient clipping affects the convergence of the incremental gradient methods on minimizing an objective function that is the sum of a large number of component functions. We show that clipping on gradients of component functions leads to bias on the descent…

Cited by 49 Source ↗PDF ↗Scholar ↗