Pay Attention to the Robustness of Chinese Minority Language Models! Syllable-level Textual Adversarial Attack on Tibetan Script
The textual adversarial attack refers to an attack method in which the attacker adds imperceptible perturbations to the original texts by elaborate design so that the NLP (natural language processing) model produces false judgments. This method is also used to evaluate the robustness of NLP models. Currently, most of the research in this field focuses on English, and there is also a certain amount of research on Chinese. However, to the best of our knowledge, there is little research targeting Chinese minority languages. Textual adversarial attacks are a new challenge for the information processing of Chinese minority languages. In response to this situation, we propose a Tibetan syllable-level black-box textual adversarial attack called TSAttacker based on syllable cosine distance and scoring mechanism. And then, we conduct TSAttacker on six models generated by fine-tuning two PLMs (pre-trained language models) for three downstream tasks. The experiment results show that TSAttacker is effective and generates high-quality adversarial samples. In addition, the robustness of the involved models still has much room for improvement.
Code (1)
Tasks
Adversarial AttackSimilar Papers 제목 키워드 기반
Multi-Granularity Tibetan Textual Adversarial Attack Method Based on Masked Language Model
In social media, neural network models have been applied to hate speech detection, sentiment analysis, etc., but neural network models are susceptible to adversarial attacks. For instance, in a text classification task, …
Adversarial AttackHate Speech DetectionLanguage ModelingLanguage Modelling+3A comparable study of modeling units for end-to-end Mandarin speech recognition
End-To-End speech recognition have become increasingly popular in mandarin speech recognition and achieved delightful performance. Mandarin is a tonal language which is different from English and requires special treat…
Decoderspeech-recognitionSpeech RecognitionSyllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese
Sequence-to-sequence attention-based models have recently shown very promising results on automatic speech recognition (ASR) tasks, which integrate an acoustic, pronunciation and language model into a single neural netwo…
Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DecoderLanguage Modeling+7CINO: A Chinese Minority Pre-trained Language Model
Multilingual pre-trained language models have shown impressive performance on cross-lingual tasks. It greatly facilitates the applications of natural language processing on low-resource languages. However, there are stil…
Language ModelingLanguage Modellingmodeltext-classification+1CINO: A Chinese Minority Pre-trained Language Model
Multilingual pre-trained language models have shown impressive performance on cross-lingual tasks. It greatly facilitates the applications of natural language processing on low-resource languages. However, there are stil…
Language ModelingLanguage Modellingmodeltext-classification+1