攻破BERT：针对Twitter情感分析中目标错误分类的梯度攻击
Breaking BERT: Gradient Attack on Twitter Sentiment Analysis for Targeted Misclassification
AI总结：
本文针对Twitter情感分析中BERT模型的固有漏洞，提出一种基于梯度和白盒方法的对抗攻击框架，通过迭代替换高影响力单词生成隐蔽的对抗文本以实现目标错误分类。
摘要：
像Twitter这样的社交媒体平台越来越依赖自然语言处理（NLP）技术来分析和理解用户生成内容中表达的情感。BERT（Bidirectional Encoder Representations from Transformers）就是这样一种最先进的NLP模型，已被广泛应用于情感分析中。BERT容易受到对抗性攻击的影响。本文旨在仔细审查此类模型在Twitter情感分析中的固有漏洞。它旨在制定一个框架，用于构建能够欺骗这些模型同时保持隐蔽性的目标对抗文本。与Importance Reweighting等传统方法相比，该框架的核心思想在于依靠梯度来确定文本中单个单词的重要性优先级。它使用白盒方法获得细粒度的敏感度，精确定位对分类结果产生最大影响的单词。本文分为三个相互依赖的阶段。首先，在Twitter数据上微调预训练的BERT模型。然后，分析模型的梯度以对单词的重要性进行排序，并迭代地将其替换为可行的候选词，直到找到可接受的解决方案。最后，评估对抗文本针对自定义训练的情感分类模型的有效性。这一评估将有助于衡量对抗文本在不引起任何警觉的情况下成功颠覆分类的能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
