all AI news
Enhance Robustness of Language Models Against Variation Attack through Graph Integration
April 19, 2024, 4:47 a.m. | Zi Xiong, Lizhi Qing, Yangyang Kang, Jiawei Liu, Hongsong Li, Changlong Sun, Xiaozhong Liu, Wei Lu
cs.CL updates on arXiv.org arxiv.org
Abstract: The widespread use of pre-trained language models (PLMs) in natural language processing (NLP) has greatly improved performance outcomes. However, these models' vulnerability to adversarial attacks (e.g., camouflaged hints from drug dealers), particularly in the Chinese language with its rich character diversity/variation and complex structures, hatches vital apprehension. In this study, we propose a novel method, CHinese vAriatioN Graph Enhancement (CHANGE), to increase the robustness of PLMs against character variation attacks in Chinese content. CHANGE presents …
abstract adversarial adversarial attacks arxiv attacks chinese cs.cl cs.cr diversity graph however integration language language models language processing natural natural language natural language processing nlp performance processing robustness through type variation vulnerability
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior Data Scientist
@ ITE Management | New York City, United States