Image de couverture de livre

Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Haotan, He, Jianfei, Ma, Jiayuan, Na, Hongbin, Wang, Zimu, Zhang, Haiyang, Chen, Qi, Wang, Wei, Shi, Zijing, Shen, Tao, Chen, Ling
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Guardians of Discourse: Evaluating LLMs on Multilingual Offensive Language Detection
par: He, Jianfei, et autres
Publié: (2024)

ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations
par: Xiao, Yunze, et autres
Publié: (2024)

Detecting Conversational Mental Manipulation with Intent-Aware Prompting
par: Ma, Jiayuan, et autres
Publié: (2024)

Thinker-DDM: Modeling Deliberation for Machine Translation with a Drift-Diffusion Process
par: Na, Hongbin, et autres
Publié: (2024)

You Never Know a Person, You Only Know Their Defenses: Detecting Levels of Psychological Defense Mechanisms in Supportive Conversations
par: Na, Hongbin, et autres
Publié: (2025)

Novel AI Camera Camouflage: Face Cloaking Without Full Disguise
par: Noever, David, et autres
Publié: (2024)

Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams
par: Li, Zirui, et autres
Publié: (2025)

A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directions
par: Na, Hongbin, et autres
Publié: (2025)

Multi-Session Client-Centered Treatment Outcome Evaluation in Psychotherapy
par: Na, Hongbin, et autres
Publié: (2024)

Effect of Phonological and Phonetic Interventions on Proficiency in English Pronunciation and Oral Reading
par: Diwakar Prahaladaiah, et autres
Publié: (2024)

MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models
par: Yu, Beibei, et autres
Publié: (2024)

Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon
par: Ma, Xuchen, et autres
Publié: (2025)

CBT-LLM: A Chinese Large Language Model for Cognitive Behavioral Therapy-based Mental Health Question Answering
par: Na, Hongbin
Publié: (2024)

Chinese Offensive Language Detection:Current Status and Future Directions
par: Xiao, Yunze, et autres
Publié: (2024)

Hazards in Daily Life? Enabling Robots to Proactively Detect and Resolve Anomalies
par: Song, Zirui, et autres
Publié: (2024)

Efficacy of Artificial Intelligence (AI) Voice Cloning in Phonetic Self‐Imitation for L2 Pronunciation Training
par: Ewa Kusz, et autres
Publié: (2025)

Exploiting Bishun to Predict the Pronunciation of Chinese
par: Chenggang Mi
Publié: (2016)

Monte Carlo Planning with Large Language Model for Text-Based Game Agents
par: Shi, Zijing, et autres
Publié: (2025)

3D Invisible Cloak
par: Xue, Mingfu, et autres
Publié: (2020)

MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations
par: Xue, Qiyao, et autres
Publié: (2025)

Language-based Audio Retrieval with Co-Attention Networks
par: Sun, Haoran, et autres
Publié: (2024)

AI Decodes Historical Chinese Archives to Reveal Lost Climate History
par: He, Sida, et autres
Publié: (2026)

Benchmarking and Improving LVLMs on Event Extraction from Multimedia Documents
par: Xing, Fuyu, et autres
Publié: (2025)

NetCloak: Dynamic Topology Expansion for Secure and Scalable Configuration Sharing
par: Wang, Qianye, et autres
Publié: (2025)

Disentangling the Drivers of LLM Social Conformity: An Uncertainty-Moderated Dual-Process Mechanism
par: Zhong, Huixin, et autres
Publié: (2025)

PathFuzzing: Worst Case Analysis by Fuzzing Symbolic-Execution Paths
par: Chen, Zimu, et autres
Publié: (2025)

Myths in Disguise
par: Głowiński, Michał
Publié: (2024)

ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation
par: Teng, Qianrui, et autres
Publié: (2025)

Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection
par: Wang, Han, et autres
Publié: (2025)

UFMylation at the Crossroads of Health and Cancer: A Blessing in Disguise
par: Congcong Li, et autres
Publié: (2026)

Transformers -- Messages in Disguise
par: Tyler, Joshua H., et autres
Publié: (2024)

LLM Safety Alignment is Divergence Estimation in Disguise
par: Haldar, Rajdeep, et autres
Publié: (2025)

An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection
par: Yan, Shenao, et autres
Publié: (2024)

Phonetic Segmentation of the UCLA Phonetics Lab Archive
par: Chodroff, Eleanor, et autres
Publié: (2024)

Cloaking Cosmic Light
par: Kaloper, Nemanja
Publié: (2026)

Experimental Realization of a One‐Directional Broadband Transmissive Cloak in Microwaves
par: Ruichen Li, et autres
Publié: (2024)

Fine-Tuning Large Multimodal Models for Automatic Pronunciation Assessment
par: Wang, Ke, et autres
Publié: (2025)

Theoretical Study on the Structure and Spectral Characteristics of Three Boron‐Doped Fullerene C27B Isomers and Their Newly Synthesized Uranium‐Embedded Derivatives
par: Tao Gao, et autres
Publié: (2025)

Evolutionary Games‐Assisted Synchronization Metasurface for Simultaneous Multisource Invisibility Cloaking
par: Min Huang, et autres
Publié: (2024)

Speech Codec Probing from Semantic and Phonetic Perspectives
par: Shi, Xuan, et autres
Publié: (2026)