Yichen Yang

Fast Gradient Projection Method for Text Adversary Generation and Adversarial Training

2020 · arXiv (Cornell University)

Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be …

Program Synthesis Guided Reinforcement Learning

2021 · arXiv (Cornell University)

A key challenge for reinforcement learning is solving long-horizon planning and control problems. Recent work has proposed leveraging programs to help guide the learning algorithm in these settings. However, these approaches impose a high manual …

Fast Adversarial Training against Textual Adversarial Attacks

2024 · arXiv (Cornell University)

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates used by attackers …