# Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon

arXiv: https://arxiv.org/abs/2505.22184 · HTML: https://mlsanity.com/paper/2505.22184/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Baichuan 2: Open Large-scale Language Models](https://mlsanity.com/paper/2309.10305/) (2023)
- [LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked](https://mlsanity.com/paper/2308.07308/) (2023)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Spelling Error Correction with Soft-Masked BERT](https://mlsanity.com/paper/2005.07421/) (2020)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check](https://mlsanity.com/paper/2004.14166/) (2020)
- [Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate](https://mlsanity.com/paper/2108.05921/) (2021)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection](https://mlsanity.com/paper/2108.03070/) (2021)
- [Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks](https://mlsanity.com/paper/2202.08011/) (2022)
- [Detecting Harmful Content On Online Platforms: What Platforms Need Vs. Where Research Efforts Go](https://mlsanity.com/paper/2103.00153/) (2021)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)
- [Defining and Detecting Toxicity on Social Media: Context and Knowledge are Key](https://mlsanity.com/paper/2104.10788/) (2021)
- [Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task](https://mlsanity.com/paper/2310.06504/) (2023)
- [Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity](https://mlsanity.com/paper/2210.10996/) (2022)
- [C-LLM: Learn to Check Chinese Spelling Errors Character by Character](https://mlsanity.com/paper/2406.16536/) (2024)
- [Target Span Detection for Implicit Harmful Content](https://mlsanity.com/paper/2403.19836/) (2024)
- [Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking](https://mlsanity.com/paper/2403.08492/) (2024)
- [A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models](https://mlsanity.com/paper/2410.04027/) (2024)
- [ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models](https://mlsanity.com/paper/2410.18491/) (2024)
- [Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph](https://mlsanity.com/paper/2412.15268/) (2024)
- [Context-Sensitive Malicious Spelling Error Correction](https://mlsanity.com/paper/1901.07688/) (2019)

## Built on by (most cited first, 1 of 1)

- [Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement](https://mlsanity.com/paper/2507.07640/) (2025)

## Abstract (arXiv)

Social media platforms have experienced a significant rise in toxic content, including abusive language and discriminatory remarks, presenting growing challenges for content moderation. Some users evade censorship by deliberately disguising toxic words through homophonic cloak, which necessitates the task of unveiling cloaked toxicity. Existing methods are mostly designed for English texts, while Chinese cloaked toxicity unveiling has not been solved yet. To tackle the issue, we propose C2TU, a novel training-free and prompt-free method for Chinese cloaked toxic content unveiling. It first employs substring matching to identify candidate toxic words based on Chinese homophone graph and toxic lexicon. Then it filters those candidates that are non-toxic and corrects cloaks to be their corresponding toxicities. Specifically, we develop two model variants for filtering, which are based on BERT and LLMs, respectively. For LLMs, we address the auto-regressive limitation in computing word occurrence probability and utilize the full semantic contexts of a text sequence to reveal cloaked toxic words. Extensive experiments demonstrate that C2TU can achieve superior performance on two Chinese toxic datasets. In particular, our method outperforms the best competitor by up to 71% on the F1 score and 35% on accuracy, respectively. Our code and data are available at https://github.com/XDxc-cuber/C2TU-Chinese-cloaked-toxicity-unveiling.