文本分类中的隐私泄漏：一种数据抽取方法
Privacy Leakage in Text Classification: A Data Extraction Approach
摘要：
最近的工作已经证明了从生成语言模型中成功地提取训练数据。然而，这是不明显的，这种提取是否是可行的文本分类模型，因为训练目标是预测类标签，而不是下一个词的预测。这提出了一个有趣的挑战，并提出了一个重要的问题，在文本分类设置的训练数据的隐私。因此，我们通过调查与学习任务无关的训练数据的非故意记忆问题来研究文本分类领域中潜在的隐私泄漏。我们提出了一种算法，通过利用模型提供的类标签的可能性来提取部分文本的缺失标记。我们通过将金丝雀插入训练集中并尝试在训练后提取这些金丝雀中的标记来测试我们算法的有效性。在我们的实验中，我们证明了成功的提取在一定程度上是可能的。这也可以用作审计策略，以评估任何未经同意的潜在未经授权使用个人数据的情况。
英文摘要：
Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict the class label as opposed to next-word prediction. This poses an interesting challenge and raises an important question regarding the privacy of training data in text classification settings. Therefore, we study the potential privacy leakage in the text classification domain by investigating the problem of unintended memorization of training data that is not pertinent to the learning task. We propose an algorithm to extract missing tokens of a partial text by exploiting the likelihood of the class label provided by the model. We test the effectiveness of our algorithm by inserting canaries into the training set and attempting to extract tokens in these canaries post-training. In our experiments, we demonstrate that successful extraction is possible to some extent. This can also be used as an auditing strategy to assess any potential unauthorized use of personal data without consent.
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。
