Daniel Lowd

The Libra Toolkit for Probabilistic Models

2015 · arXiv (Cornell University)

The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models, including Bayesian networks, Markov networks, dependency networks, and sum-product networks. Compared to other toolkits, Libra places a greater emphasis …

Identifying Adversarial Attacks on Text Classifiers

2022 · arXiv (Cornell University)

The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a …

On Adversarial Examples for Character-Level Neural Machine Translation

2018 · arXiv (Cornell University)

Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Due to the difficulty of creating white-box adversarial examples for discrete text input, most analyses of the robustness of …