mlsanityData to 14 Oct 2026

Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttack

arXiv 2506.23661 ↗First posted 30 Jun 2025cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

12 of 19 references.

References · 12

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  4. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 671
  5. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
  6. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 381
  7. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 345
  8. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  9. 2021A Strong Baseline for Query Efficient Attacks in a Black Box Settingcited by 16
  10. 2023Verifying the Robustness of Automatic Credibility Assessmentcited by 8
  11. 2023BeamAttack: Generating High-quality Textual Adversarial Examples through Beam Search and Mixed Semantic Spacescited by 5
  12. 2024OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generationcited by 4

Built on by

Not cited yet.