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

2022/02/11 by Shahrukh Rafi Khan, Khan, Shahrukh, Mahnoor Shahid +3
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Natural Language Processing Techniques

paper · pdf · doi:10.48550/arxiv.2202.05778

openalex publication_date 2022/02/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• HateBERT: Retraining BERT for Abusive Language Detection in English
• Feature Selection Empowered BERT for Detection of Hate Speech with Vocabulary Augmentation
• Human-in-the-Loop Hate Speech Classification in a Multilingual Context
• BERT-ATTACK: Adversarial Attack Against BERT Using BERT
• Hate Speech Targets Detection in Parler using BERT