What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations BlackboxNLP EMNLP

Zhouhang Xie | Jonathan Brophy | Adam Noack | Wencong You | Kalyani Asthana | Carter Perkins | Sabrina Reis | Zayd Hammoudeh | Daniel Lowd | Sameer Singh |

On Adversarial Examples for Character-Level Neural Machine Translation COLING

Javid Ebrahimi | Daniel Lowd | Dejing Dou |

HotFlip: White-Box Adversarial Examples for Text Classification ACL

Javid Ebrahimi | Anyi Rao | Daniel Lowd | Dejing Dou |

A Joint Sentiment-Target-Stance Model for Stance Classification in Tweets COLING

Javid Ebrahimi | Dejing Dou | Daniel Lowd |

Weakly Supervised Tweet Stance Classification by Relational Bootstrapping EMNLP

Javid Ebrahimi | Dejing Dou | Daniel Lowd |