Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack
We extend BeamAttack, an adversarial attack algorithm designed to evaluate the robustness of text classification systems through word-level modifications guided by beam search. Our extensions include support for word deletions and the option to skip substitutions, enabling the discovery of minimal modifications that alter model predictions. We also integrate LIME to better prioritize word replacements. Evaluated across multiple datasets and victim models (BiLSTM, BERT, and adversarially trained RoBERTa) within the BODEGA framework, our approach achieves over a 99\% attack success rate while preserving the semantic and lexical similarity of the original texts. Through both quantitative and qualitative analysis, we highlight BeamAttack's effectiveness and its limitations. Our implementation is available at https://github.com/LucK1Y/BeamAttack
Code (1)
Tasks
Adversarial AttackMisinformationtext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation
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 AttackAdversarial TextEnsemble LearningMisinformation+3Attacking Misinformation Detection Using Adversarial Examples Generated by Language Models
We investigate the challenge of generating adversarial examples to test the robustness of text classification algorithms detecting low-credibility content, including propaganda, false claims, rumours and hyperpartisan ne…
ArticlesMisinformationRumour DetectionStyle Transfer+3Understanding Adversarial Examples Through Deep Neural Network's Response Surface and Uncertainty Regions
Deep neural network (DNN) is a popular model implemented in many systems to handle complex tasks such as image classification, object recognition, natural language processing etc. Consequently DNN structural vulnerabilit…
Classificationimage-classificationImage ClassificationObject RecognitionEvaluating Text Classification Robustness to Part-of-Speech Adversarial Examples
As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in the face of adversarial examples. Adversa…
Decision Makingtext-classificationText ClassificationAdversarial Machine Learning And Speech Emotion Recognition: Utilizing Generative Adversarial Networks For Robustness
Although deep learning has enabled unprecedented improvements in the performance of the state-of-the-art speech emotion recognition (SER) systems, recent research on adversarial examples has cast a shadow of doubt on th…
Adversarial AttackBIG-bench Machine LearningEmotion RecognitionGenerative Adversarial Network+1