Abstract
Social media platforms like Twitter have increasingly relied on Natural Language Processing NLP techniques to analyze and understand the sentiments expressed in the user generated content. One such state of the art NLP model is Bidirectional Encoder Representations from Transformers BERT which has been widely adapted in sentiment analysis. BERT is susceptible to adversarial attacks. This paper aims to scrutinize the inherent vulnerabilities of such models in Twitter sentiment analysis. It aims to formulate a framework for constructing targeted adversarial texts capable of deceiving these models, while maintaining stealth. In contrast to conventional methodologies, such as Importance Reweighting, this framework core idea resides in its reliance on gradients to prioritize the importance of individual words within the text. It uses a whitebox approach to attain fine grained sensitivity, pinpointing words that exert maximal influence on the classification outcome. This paper is organized into three interdependent phases. It starts with fine-tuning a pre-trained BERT model on Twitter data. It then analyzes gradients of the model to rank words on their importance, and iteratively replaces those with feasible candidates until an acceptable solution is found. Finally, it evaluates the effectiveness of the adversarial text against the custom trained sentiment classification model. This assessment would help in gauging the capacity of the adversarial text to successfully subvert classification without raising any alarm.
Abstract (translated)
社交媒体平台如Twitter越来越多地依赖自然语言处理（NLP）技术来分析和理解用户生成内容中的情感。其中，转换器模型的双向编码表示法（BERT）是一种最先进的NLP模型，在情感分析中被广泛应用。然而，BERT对对抗性攻击较为脆弱。本文旨在审查这类模型在推特情感分析中的内在脆弱性，并构建一个框架以构造能够欺骗这些模型的针对性对抗文本，同时保持隐蔽性。 与传统的诸如重要性重权（Importance Reweighting）等方法不同，该框架的核心理念在于利用梯度来确定文本中各个单词的重要性。它采用白盒方法实现精细级的敏感度分析，识别对分类结果影响最大的词汇。本文分为三个相互依赖的阶段：首先，基于推特数据微调预训练的BERT模型；其次，通过分析模型的梯度来排序词的重要程度，并迭代替换这些词直到找到可行方案；最后，评估对抗文本在自定义训练的情感分类模型上的有效性。 这种评估有助于衡量对抗性文本成功误导分类而不引起怀疑的能力。
URL
https://arxiv.org/abs/2504.01345
