paper-with-me

홈 › Papers

Harder to Defend: Towards Chinese Toxicity Attacks via Implicit Enhancement and Obfuscation Rewriting

2026-05-21 · Jingyi Kang, Junyu Lu, Bo Xu, Hongbo Wang, Linlin zong, Roy Ka-Wei Lee, Hongfei Lin arxiv

Large language models (LLMs) require robust toxicity evaluation beyond explicit wording. This setting remains underexplored in Chinese, where toxicity may combine semantic indirectness with surface obfuscation. We introduce Chinese Implicit Toxicity Attack (CITA), a controlled red-team evaluation and defense-data generation framework, not a deployable evasion tool. CITA uses three stages: (i) Harmful Intent Learning, (ii) Implicit Toxicity Enhancement, and (iii) Obfuscation Variant Rewriting, to preserve harmful intent, increase implicitness, and add controlled surface variants. On CITA-generated evaluation samples, the seven tested detectors exhibit substantial missed-detection risks, reaching an average ASR of 69.48%; human evaluation further confirms preserved harmfulness and increased implicitness/evasiveness. As a downstream defense application, we fine-tune a Chinese Implicit Toxicity Defense model (CITD) with CITA-generated red-team data, showing that such data can improve robustness through additional training.

📄 PDF Abstract BibTeX arXiv:2605.22258

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ASTPrompter: Weakly Supervised Automated Language Model Red-Teaming to Identify Low-Perplexity Toxic Prompts

2024-07-12 · Amelia F. Hardy, Houjun Liu, Bernard Lange, Duncan Eddy 외

Conventional approaches for the automated red-teaming of large language models (LLMs) aim to identify prompts that elicit toxic outputs from a frozen language model (the defender). This often results in the prompting mod…

Language ModelingLanguage ModellingRed Teaming

Towards Robust Toxic Content Classification

2019-12-14 · Keita Kurita, Anna Belova, Antonios Anastasopoulos

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a m…

ClassificationDenoisingGeneral Classification

Fortifying Toxic Speech Detectors Against Veiled Toxicity

2020-10-07 · EMNLP 2020 11 · Xiaochuang Han, Yulia Tsvetkov

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large an…

Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks

2020-10-24 · Huimin Zeng, Chen Zhu, Tom Goldstein, Furong Huang

Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attac…

Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks

2023-05-08 · Junyu Lu, Bo Xu, Xiaokun Zhang, Changrong Min 외

The widespread dissemination of toxic online posts is increasingly damaging to society. However, research on detecting toxic language in Chinese has lagged significantly. Existing datasets lack fine-grained annotation of…

Hate Speech Detection