mlsanityData to 7 Oct 2026

White-Box Attacks on Hate-speech BERT Classifiers in German with Explicit and Implicit Character Level Defense

arXiv 2202.05778 ↗First posted 11 Feb 2022cs.CLcited by 1

Not on the map. Why?

Abstract (arXiv)

In this work, we evaluate the adversarial robustness of BERT models trained on German Hate Speech datasets. We also complement our evaluation with two novel white-box character and word level attacks thereby contributing to the range of attacks available. Furthermore, we also perform a comparison of two novel character-level defense strategies and evaluate their robustness with one another.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 25 references that are in the map. First posted on arXiv 11 Feb 2022.

Builds on

18 of 25 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2015Towards Open Set Deep Networkscited by 533
  11. 2020BAE: BERT-based Adversarial Examples for Text Classificationcited by 316
  12. 2017On Detecting Adversarial Perturbationscited by 232
6 more
  1. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
  2. 2019Combating Adversarial Misspellings with Robust Word Recognitioncited by 162
  3. 2020German's Next Language Modelcited by 144
  4. 2017Adversarial and Clean Data Are Not Twinscited by 52
  5. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 34
  6. 2019Deep Neural Rejection against Adversarial Examplescited by 31

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Cracking the Code: Enhancing Implicit Hate Speech Detection through Coding Classificationcited by 2