Reproduce “Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Thai Le, Jooyoung Lee, Kevin Yen, Yifan Hu, Dongwon Lee

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.