Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
summary
The gist
The gist The C2TU method proposes a novel training-free and prompt-free approach for Chinese cloaked toxicity unveiling by employing substring matching with a homophone graph and filtering candidates
In short
C$^2$TU is a novel, training-free method for identifying hidden toxic words in Chinese text that are disguised using homophones or similar sounds. It works by first finding potential toxic words using a graph of Chinese homophones and a known toxic word list. Then, it filters these candidates using either BERT or LLMs to correct the cloaks into their actual toxic meanings, achieving superior results on Chinese toxicity datasets.
Key concepts
- Homophone Graph
- This is a map created by connecting all Chinese characters that sound alike or share phonetic similarities, including dialectal relationships like 'n' and 'l'. This graph helps the method find potential toxic words that are written using different characters but pronounced similarly, which is a common way users hide toxicity.
- Toxic Lexicon
- This is a curated list of actual toxic words. The method uses this list to identify the 'proto' or true form of a word, such as '垃圾', and then looks for cloaked versions like '辣鸡' that might be used instead. This external knowledge helps narrow down the search space for toxic content.
- ProbDiff (Probability Difference)
- This is a mathematical measure calculated between the probability of the cloaked word ($P_w$) and its potential true word ($P_l$). A larger difference indicates a stronger likelihood that the cloaked word is actually a toxic term. This difference is used iteratively to select the most likely correct replacement for each candidate.
- BERT/LLM Filtering Variants
- The method uses two different models—BERT and Large Language Models (LLMs)—to filter candidates. BERT uses its Masked Language Modeling task to calculate word-level probability differences. LLMs are used by reformulating these differences into sentence-level probabilities, allowing them to capture the full context of the text for better unveiling.
Terminology used across episodes
This episode discusses
- Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon · Paper Radio
- SpellGCN: Incorporating Phonological and Visual Similarities into Language Models for Chinese Spelling Check
- COLD: A Benchmark for Chinese Offensive Language Detection
- Rich Semantic Knowledge Enhanced Large Language Models for Few-shot Chinese Spell Checking
- AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts
- Improving Chinese Spelling Check by Character Pronunciation Prediction: The Effects of Adaptivity and Granularity
- C-LLM: Learn to Check Chinese Spelling Errors Character by Character
- DeepSeek-V3 Technical Report
- Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks
- LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
- ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations
- Baichuan 2: Open Large-scale Language Models
- ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
- Spelling Error Correction with Soft-Masked BERT
- Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
- A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models
The paper
Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon · Read on arXiv
Xuchen Ma, Jianxiang Yu, Wenming Shao, Bo Pang, Xiang Li
School of Data Science and Engineering, East China Normal University
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 C squared TU, 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 C squared TU 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.
Transcript
Introduction to the show: ident: AI Radio. Generated commentary on the latest Artificial Intelligence papers.
Tom: Today's paper: "Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon".
Jane: The gist The C2TU method proposes a novel training-free and prompt-free approach for Chinese cloaked toxicity unveiling by employing substring matching with a homophone graph and filtering candidates using both…
Tom: First, who's behind it and why it matters.
Paper summary: Tom: So we’ve touched on what this paper is about, but let's dig into the specifics now about "Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon." The authors are trying to solve the problem of toxic content evasion through homophonic cloaks in Chinese, which they say existing tools designed for English just don't work.
Jane: They propose C squared TU, which is training-free and prompt-free <ref:2505.22184#pg1,training-free and prompt-free>. They start by using substring matching against a Chinese homophone graph and a toxic lexicon to identify candidate toxic words that match the length of known toxic words.
Lu: The matching stage generates these candidate pairs denoted as Wp equals w(i), l(i), where l(i) is a probable toxic unveiling of w(i) based on the homophone graph and lexicon, as described in Algorithm one on page sixteen.
Meng: Then they move to filtering those candidates, refining them by calculating the probability difference between the word and its potential replacement using either BERT or LLMs, which is defined by ProbDiff Pw l equals log Pw minus log Pl equals log Pw/Pl, as detailed in Section three point four on page five.
Lalam: For BERT filtering, they use a Masked Language Modeling task where they compute the probability difference using Equation three on page five to reveal cloaked toxic words based on larger probabilities and for LLMs, they handle the auto-regressive limitation by reformulating word-level probability differences into sentence-level ones using Bayes’ theorem as shown in Theorem one and Equation nine on page thirteen.
Tom: So, essentially, it’s a two-stage process: first identifying potential matches through matching, and then filtering those candidates iteratively by finding the most significant probability gap using either BERT or LLMs to correct the cloaks into their proto toxic words.
Jane: The authors specifically construct a homophone graph G equals (N, E) involving extracting all Chinese characters and connecting them with identical pinyin or phonetically similar pronunciations, including dialectal relationships like “n” ↔ “l” or “zh” ↔ “z”, as described in Section three point one.one on page three.
Lu: They also build a toxic lexicon L equals (l1, · · ·, lm) which is designed to be simple and clean by retaining only the proto words, like keeping “垃圾” la j¯ı while using “辣鸡” là j¯ı as a cloaked substitution, according to Section three point one.two on page three.
Meng: The filtering step itself involves iteratively replacing the pair with the most significant gap where di equals ProbDiff Pw i Pl i is calculated, and then selecting the index k equals argmin i di in Algorithm two on page sixteen which basically finds the largest difference.
Lalam: And their experimental results are pretty strong. They showed C2TU-LLM achieving an F1 score of seventy-four point six seven percent on the ToxicloakCN dataset and ninety point five two percent on COLDataset, outperforming the best competitor by up to seventy-one percent on the F1 score as shown in Table one on page seven.
Tom: That’s a substantial gap, nearly three times better than the top baselines they compared it against, which really shows how this method handles Chinese cloaked toxicity effectively.
Conclusion: Jane: So we’ve gone through the paper "Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon," and what it means for the world is that we finally have a tool specifically built for Chinese language toxicity that doesn't require extensive training or complex prompting.
Lu: The C squared TU method successfully combines substring matching with iterative filtering using either BERT or LLMs to correct cloaks into their proto toxic words, and they demonstrate superior performance on the ToxicloakCN and COLDataset datasets <ref:2505.22184#pg1>.
Meng: For people building moderation tools, this means they can expect a system that is not just good at spotting toxicity but also actually correcting the deceptive language users employ to bypass filters.
Lalam: It shows that leveraging full semantic context through those sentence probability differences allows this method to outperform existing techniques by up to seventy-one percent on the F1 score and thirty-five percent on accuracy, which is a big jump.
Tom: The title itself, "Breaking the Cloak!", captures the essence of what they did—they managed to peel back that deliberate disguise using linguistic structure and probability calculations specific to Chinese.
Jane: The authors are Xuchen Ma, Jianxiang Yu, Wenming Shao, Bo Pang, and Xiang Li at East China Normal University. Their work moves us closer to creating more robust safety measures for online Chinese platforms by tackling the unique challenges of homophonic cloaking.
More episodes
- 2510.22654-Managing Self-Learning Experts under Per-Round Budget Constraints
- 2405.01930-OARelatedWork: A Large-Scale Dataset of Related Work Sections with Full-texts from Open Access Sources
- 2412.12478-Human-in-the-Loop Generation of Adversarial Texts: A Case Study on Tibetan Script
- 2502.01025-Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
- 2504.02891-Automated Survey Collection with LLM-based Conversational Agents
- 2505.17244-ReasoningShield: Safety Detection over Reasoning Traces of Large Reasoning Models
- 2510.10998-ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
- 2510.13154-The Alignment Veto: How Safety Training Suppresses Cultural Knowledge in LLMs
- 2601.17898-Assessment of Generative Named Entity Recognition in the Era of Large Language Models
- 2601.18901-Self-Aware Knowledge Probing: Evaluating Language Models' Relational Knowledge through Confidence Calibration