Xuan Feng

Harnessing the Power of LLM to Support Binary Taint Analysis

2023 · arXiv (Cornell University)

This paper proposes LATTE, the first static binary taint analysis that is powered by a large language model (LLM). LATTE is superior to the state of the art (e.g., Emtaint, Arbiter, Karonte) in three aspects. …

Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction

2024 · arXiv (Cornell University)

Unnatural text correction aims to automatically detect and correct spelling errors or adversarial perturbation errors in sentences. Existing methods typically rely on fine-tuning or adversarial training to correct errors, which have achieved significant success. However, …