mlsanityData to 7 Oct 2026

GenFighter: A Generative and Evolutive Textual Attack Removal

arXiv 2404.11538 ↗First posted 17 Apr 2024cs.LG cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP). This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution. GenFighter identifies potentially malicious instances deviating from the distribution, transforms them into semantically equivalent instances aligned with the training data, and employs ensemble techniques for a unified and robust response. By conducting extensive experiments, we show that GenFighter outperforms state-of-the-art defenses in accuracy under attack and attack success rate metrics. Additionally, it requires a high number of queries per attack, making the attack more challenging in real scenarios. The ablation study shows that our approach integrates transfer learning, a generative/evolutive procedure, and an ensemble method, providing an effective defense against NLP adversarial attacks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 17 Apr 2024.

Builds on

33 of 55 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  9. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  10. 2019Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailmentcited by 663
  11. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  12. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 488
21 more
  1. 2018Generating Natural Language Adversarial Examplescited by 422
  2. 2019PAWS: Paraphrase Adversaries from Word Scramblingcited by 395
  3. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  4. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  5. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  6. 2019FreeLB: Enhanced Adversarial Training for Natural Language Understandingcited by 261
  7. 2019Certified Robustness to Adversarial Word Substitutionscited by 164
  8. 2017Deep Text Classification Can be Fooledcited by 105
  9. 2019Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagationcited by 87
  10. 2020OpenAttack: An Open-source Textual Adversarial Attack Toolkitcited by 84
  11. 2020Robustness Verification for Transformerscited by 76
  12. 2020SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutionscited by 72
  13. 2021Towards Robustness Against Natural Language Word Substitutionscited by 68
  14. 2024Defending LLMs against Jailbreaking Attacks via Backtranslationcited by 65
  15. 2020Do We Need Zero Training Loss After Achieving Zero Training Error?cited by 61
  16. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  17. 2021Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitutioncited by 55
  18. 2019Natural Language Adversarial Defense through Synonym Encodingcited by 39
  19. 2020Better Robustness by More Coverage: Adversarial Training with Mixup Augmentation for Robust Fine-tuningcited by 39
  20. 2021A Strong Baseline for Query Efficient Attacks in a Black Box Settingcited by 16
  21. 2023Randomized Smoothing with Masked Inference for Adversarially Robust Text Classificationscited by 11

Built on by

Not cited yet.