Anupam Datta

Gender Bias in Neural Natural Language Processing

2018 · arXiv (Cornell University)

We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with …

CASH: A Cost Asymmetric Secure Hash Algorithm for Optimal Password Protection

2015 · arXiv (Cornell University)

An adversary who has obtained the cryptographic hash of a user's password can mount an offline attack to crack the password by comparing this hash value with the cryptographic hashes of likely password guesses. This …