Wei Fang


Where to Attack: A Dynamic Locator Model for Backdoor Attack in Text Classifications
Heng-yang Lu | Chenyou Fan | Jun Yang | Cong Hu | Wei Fang | Xiao-jun Wu
Proceedings of the 29th International Conference on Computational Linguistics

Nowadays, deep-learning based NLP models are usually trained with large-scale third-party data which can be easily injected with malicious backdoors. Thus, BackDoor Attack (BDA) study has become a trending research to help promote the robustness of an NLP system. Text-based BDA aims to train a poisoned model with both clean and poisoned texts to perform normally on clean inputs while being misled to predict those trigger-embedded texts as target labels set by attackers. Previous works usually choose fixed Positions-to-Poison (P2P) first, then add triggers upon those positions such as letter insertion or deletion. However, considering the positions of words with important semantics may vary in different contexts, fixed P2P models are severely limited in flexibility and performance. We study the text-based BDA from the perspective of automatically and dynamically selecting P2P from contexts. We design a novel Locator model which can predict P2P dynamically without human intervention. Based on the predicted P2P, four effective strategies are introduced to show the BDA performance. Experiments on two public datasets show both tinier test accuracy gap on clean data and higher attack success rate on poisoned ones. Human evaluation with volunteers also shows the P2P predicted by our model are important for classification. Source code is available at https://github.com/jncsnlp/LocatorModel


Neural Multi-Task Learning for Stance Prediction
Wei Fang | Moin Nadeem | Mitra Mohtarami | James Glass
Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)

We present a multi-task learning model that leverages large amount of textual information from existing datasets to improve stance prediction. In particular, we utilize multiple NLP tasks under both unsupervised and supervised settings for the target stance prediction task. Our model obtains state-of-the-art performance on a public benchmark dataset, Fake News Challenge, outperforming current approaches by a wide margin.

FAKTA: An Automatic End-to-End Fact Checking System
Moin Nadeem | Wei Fang | Brian Xu | Mitra Mohtarami | James Glass
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

We present FAKTA which is a unified framework that integrates various components of a fact-checking process: document retrieval from media sources with various types of reliability, stance detection of documents with respect to given claims, evidence extraction, and linguistic analysis. FAKTA predicts the factuality of given claims and provides evidence at the document and sentence level to explain its predictions.


Entity Disambiguation by Knowledge and Text Jointly Embedding
Wei Fang | Jianwen Zhang | Dilin Wang | Zheng Chen | Ming Li
Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning