Robust Rumor Detection based on Multi-Defense Model Ensemble
The development of adversarial technology, represented by adversarial text, has brought new challenges to rumor detection based on deep learning. In order to improve the robustness of rumor detection models under adversarial conditions, we propose a robust detection method based on the ensemble of m...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2023-12-01
|
Series: | Applied Artificial Intelligence |
Online Access: | http://dx.doi.org/10.1080/08839514.2022.2151174 |
_version_ | 1797684839376224256 |
---|---|
author | Fan Yang Shaomei Li |
author_facet | Fan Yang Shaomei Li |
author_sort | Fan Yang |
collection | DOAJ |
description | The development of adversarial technology, represented by adversarial text, has brought new challenges to rumor detection based on deep learning. In order to improve the robustness of rumor detection models under adversarial conditions, we propose a robust detection method based on the ensemble of multi-defense model on the basis of several mainstream defense methods such as data enhancement, random smoothing, and adversarial training. First, multiple robust detection models are trained based on different defense principles; then, two different ensemble strategies are used to integrate the above models, and the detection effect under different ensemble strategies is studied. The test results on the open-source dataset Twitter15 show that the proposed method is able to compensate for the shortcomings of a single model by ensembling different decision boundaries to effectively defend against mainstream adversarial text attacks and improve the robustness of rumor detection models compared to existing defense methods. |
first_indexed | 2024-03-12T00:35:32Z |
format | Article |
id | doaj.art-d47f2ca173cc48d1b409545b3dca6106 |
institution | Directory Open Access Journal |
issn | 0883-9514 1087-6545 |
language | English |
last_indexed | 2024-03-12T00:35:32Z |
publishDate | 2023-12-01 |
publisher | Taylor & Francis Group |
record_format | Article |
series | Applied Artificial Intelligence |
spelling | doaj.art-d47f2ca173cc48d1b409545b3dca61062023-09-15T10:01:05ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452023-12-0137110.1080/08839514.2022.21511742151174Robust Rumor Detection based on Multi-Defense Model EnsembleFan Yang0Shaomei Li1Information Engineering UniversityInformation Engineering UniversityThe development of adversarial technology, represented by adversarial text, has brought new challenges to rumor detection based on deep learning. In order to improve the robustness of rumor detection models under adversarial conditions, we propose a robust detection method based on the ensemble of multi-defense model on the basis of several mainstream defense methods such as data enhancement, random smoothing, and adversarial training. First, multiple robust detection models are trained based on different defense principles; then, two different ensemble strategies are used to integrate the above models, and the detection effect under different ensemble strategies is studied. The test results on the open-source dataset Twitter15 show that the proposed method is able to compensate for the shortcomings of a single model by ensembling different decision boundaries to effectively defend against mainstream adversarial text attacks and improve the robustness of rumor detection models compared to existing defense methods.http://dx.doi.org/10.1080/08839514.2022.2151174 |
spellingShingle | Fan Yang Shaomei Li Robust Rumor Detection based on Multi-Defense Model Ensemble Applied Artificial Intelligence |
title | Robust Rumor Detection based on Multi-Defense Model Ensemble |
title_full | Robust Rumor Detection based on Multi-Defense Model Ensemble |
title_fullStr | Robust Rumor Detection based on Multi-Defense Model Ensemble |
title_full_unstemmed | Robust Rumor Detection based on Multi-Defense Model Ensemble |
title_short | Robust Rumor Detection based on Multi-Defense Model Ensemble |
title_sort | robust rumor detection based on multi defense model ensemble |
url | http://dx.doi.org/10.1080/08839514.2022.2151174 |
work_keys_str_mv | AT fanyang robustrumordetectionbasedonmultidefensemodelensemble AT shaomeili robustrumordetectionbasedonmultidefensemodelensemble |