# Obfuscation Rules for Detecting and Detoxifying Korean Toxicity

arXiv: https://arxiv.org/abs/2510.10961 · HTML: https://mlsanity.com/paper/2510.10961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 28 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 14 of 14)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://mlsanity.com/paper/2109.05322/) (2021)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [Understanding Abuse: A Typology of Abusive Language Detection Subtasks](https://mlsanity.com/paper/1705.09899/) (2017)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection](https://mlsanity.com/paper/2411.01077/) (2024)
- [UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation](https://mlsanity.com/paper/2504.20500/) (2025)
- [CMD: a framework for Context-aware Model self-Detoxification](https://mlsanity.com/paper/2308.08295/) (2023)
- [Emoti-Attack: Zero-Perturbation Adversarial Attacks on NLP Systems via Emoji Sequences](https://mlsanity.com/paper/2502.17392/) (2025)
- [K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in Korean](https://mlsanity.com/paper/2506.13513/) (2025)
- [Identifying and Categorizing Offensive Language in Social Media](https://mlsanity.com/paper/2104.04871/) (2021)

## Abstract (arXiv)

As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions. In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation. However, obfuscation in Korean remains largely unexplored, which motivates us to introduce a KOTOX: Korean toxic dataset for deobfuscation and detoxification. We categorize Korean obfuscation patterns into linguistically grounded classes, define transformation rules derived from real-world examples, and provide the resulting obfuscation framework as an open transformation package. Using these rules, we provide paired neutral and toxic sentences alongside their obfuscated counterparts. Models trained on our dataset better handle obfuscated text without sacrificing performance on non-obfuscated text. This is the first dataset that simultaneously supports deobfuscation and detoxification for the Korean language. We expect the dataset to facilitate better understanding and mitigation of obfuscated toxic content in LLM for Korean. Our code and data are available at https://github.com/leeyejin1231/KOTOX.