小心有毒词嵌入：探索NLP模型中嵌入层的脆弱性
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
摘要：
最近的研究揭示了自然语言处理（NLP）模型的安全威胁，称为后门攻击。受害者模型可以在干净的样本上保持竞争性能，而在插入特定触发词的样本上表现异常。以前的后门攻击方法通常假设攻击者具有一定程度的数据知识，无论是用户将使用的数据集还是类似任务的代理数据集，以实现数据投毒过程。然而，在本文中，我们发现可以通过修改单个词嵌入向量来以无数据的方式破解模型，而在干净的样本上几乎没有牺牲准确性。在情感分析和配对分类任务上的实验结果表明，该方法具有更高的效率和更高的隐蔽性。我们希望这项工作可以提高人们对隐藏在NLP模型嵌入层中的这种关键安全风险的认识。我们的代码可在https://github.com/lancopku/Embedding-Poisoning上获得。
英文摘要：
Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific trigger word inserted. Previous backdoor attacking methods usually assume that attackers have a certain degree of data knowledge, either the dataset which users would use or proxy datasets for a similar task, for implementing the data poisoning procedure. However, in this paper, we find that it is possible to hack the model in a data-free way by modifying one single word embedding vector, with almost no accuracy sacrificed on clean samples. Experimental results on sentiment analysis and sentence-pair classification tasks show that our method is more efficient and stealthier. We hope this work can raise the awareness of such a critical security risk hidden in the embedding layers of NLP models. Our code is available at https://github.com/lancopku/Embedding-Poisoning.
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。
