Saved in:
Bibliographic Details
Main Authors: Lewoniewski, Włodzimierz, Stolarski, Piotr, Stróżyna, Milena, Lewańska, Elzbieta, Wojewoda, Aleksandra, Księżniak, Ewelina, Sawiński, Marcin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.02649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929487132753920
author Lewoniewski, Włodzimierz
Stolarski, Piotr
Stróżyna, Milena
Lewańska, Elzbieta
Wojewoda, Aleksandra
Księżniak, Ewelina
Sawiński, Marcin
author_facet Lewoniewski, Włodzimierz
Stolarski, Piotr
Stróżyna, Milena
Lewańska, Elzbieta
Wojewoda, Aleksandra
Księżniak, Ewelina
Sawiński, Marcin
contents This paper presents the experiments and results for the CheckThat! Lab at CLEF 2024 Task 6: Robustness of Credibility Assessment with Adversarial Examples (InCrediblAE). The primary objective of this task was to generate adversarial examples in five problem domains in order to evaluate the robustness of widely used text classification methods (fine-tuned BERT, BiLSTM, and RoBERTa) when applied to credibility assessment issues. This study explores the application of ensemble learning to enhance adversarial attacks on natural language processing (NLP) models. We systematically tested and refined several adversarial attack methods, including BERT-Attack, Genetic algorithms, TextFooler, and CLARE, on five datasets across various misinformation tasks. By developing modified versions of BERT-Attack and hybrid methods, we achieved significant improvements in attack effectiveness. Our results demonstrate the potential of modification and combining multiple methods to create more sophisticated and effective adversarial attack strategies, contributing to the development of more robust and secure systems.
format Preprint
id arxiv_https___arxiv_org_abs_2409_02649
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
Lewoniewski, Włodzimierz
Stolarski, Piotr
Stróżyna, Milena
Lewańska, Elzbieta
Wojewoda, Aleksandra
Księżniak, Ewelina
Sawiński, Marcin
Computation and Language
Artificial Intelligence
This paper presents the experiments and results for the CheckThat! Lab at CLEF 2024 Task 6: Robustness of Credibility Assessment with Adversarial Examples (InCrediblAE). The primary objective of this task was to generate adversarial examples in five problem domains in order to evaluate the robustness of widely used text classification methods (fine-tuned BERT, BiLSTM, and RoBERTa) when applied to credibility assessment issues. This study explores the application of ensemble learning to enhance adversarial attacks on natural language processing (NLP) models. We systematically tested and refined several adversarial attack methods, including BERT-Attack, Genetic algorithms, TextFooler, and CLARE, on five datasets across various misinformation tasks. By developing modified versions of BERT-Attack and hybrid methods, we achieved significant improvements in attack effectiveness. Our results demonstrate the potential of modification and combining multiple methods to create more sophisticated and effective adversarial attack strategies, contributing to the development of more robust and secure systems.
title OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.02649