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

2022-02-11 · Shahrukh Khan, Mahnoor Shahid, Navdeeppal Singh

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.

📄 PDF Abstract BibTeX arXiv:2202.05778

Code (1)

shahrukhx01/adversarial-bert-german-attacks-defense 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Adam 설명 없음

Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…

Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

WordPiece 설명 없음

Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model

2020-08-14 · Marzieh Mozafari, Reza Farahbakhsh, Noel Crespi

Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detect…

Abusive Language Hate Speech Detection Language Modelling Transfer Learning

Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERT

2020-10-01 · Hind Saleh Alatawi, Areej Maatog Alhothali, Kawthar Mustafa Moria

White supremacists embrace a radical ideology that considers white people superior to people of other races. The critical influence of these groups is no longer limited to social media; they also have a significant effec…

Language Modelling

Towards non-toxic landscapes: Automatic toxic comment detection using DNN

2019-11-19 · LREC 2020 5 · Ashwin Geet D'Sa, Irina Illina, Dominique Fohr

The spectacular expansion of the Internet has led to the development of a new research problem in the field of natural language processing: automatic toxic comment detection, since many countries prohibit hate speech in …

Binary Classification

Character-level HyperNetworks for Hate Speech Detection

2021-11-11 · Tomer Wullach, Amir Adler, Einat Minkov

The massive spread of hate speech, hateful content targeted at specific subpopulations, is a problem of critical social importance. Automated methods of hate speech detection typically employ state-of-the-art deep learni…

Data Augmentation Hate Speech Detection

Are Chess Discussions Racist? An Adversarial Hate Speech Data Set

2020-11-20 · Rupak Sarkar, Ashiqur R. KhudaBukhsh

On June 28, 2020, while presenting a chess podcast on Grandmaster Hikaru Nakamura, Antonio Radi\'c's YouTube handle got blocked because it contained "harmful and dangerous" content. YouTube did not give further specific …