Robustness Analysis of Grover for Machine-Generated News Detection
Rinaldo Gagiano, Maria Myung-Hee Kim, Xiuzhen Zhang, Jennifer Biggs
Abstract
Advancements in Natural Language Generation have raised concerns on its potential misuse for deep fake news. Grover is a model for both generation and detection of neural fake news. While its performance on automatically discriminating neural fake news surpassed GPT-2 and BERT, Grover could face a variety of adversarial attacks to deceive detection. In this work, we present an investigation of Groverâs susceptibility to adversarial attacks such as character-level and word-level perturbations. The experiment results show that even a singular character alteration can cause Grover to fail, affecting up to 97% of target articles with unlimited attack attempts, exposing a lack of robustness. We further analyse these misclassified cases to highlight affected words, identify vulnerability within Groverâs encoder, and perform a novel visualisation of cumulative classification scores to assist in interpreting model behaviour.- Anthology ID:
- 2021.alta-1.12
- Volume:
- Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association
- Month:
- December
- Year:
- 2021
- Address:
- Online
- Editors:
- Afshin Rahimi, William Lane, Guido Zuccon
- Venue:
- ALTA
- SIG:
- Publisher:
- Australasian Language Technology Association
- Note:
- Pages:
- 119–127
- Language:
- URL:
- https://aclanthology.org/2021.alta-1.12
- DOI:
- Cite (ACL):
- Rinaldo Gagiano, Maria Myung-Hee Kim, Xiuzhen Zhang, and Jennifer Biggs. 2021. Robustness Analysis of Grover for Machine-Generated News Detection. In Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association, pages 119–127, Online. Australasian Language Technology Association.
- Cite (Informal):
- Robustness Analysis of Grover for Machine-Generated News Detection (Gagiano et al., ALTA 2021)
- PDF:
- https://preview.aclanthology.org/add_acl24_videos/2021.alta-1.12.pdf
- Data
- RealNews