arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2001.02438cs.LGcs.CRcs.IRstat.ML
收藏

转移还是不转移:对转移学习文本分类器的误分类攻击

To Transfer or Not to Transfer: Misclassification Attacks Against Transfer Learned Text Classifiers

Cornell University(康奈尔大学);Microsoft Research(微软研究院)

Bijeeta Pal, Shruti Tople

摘要:

迁移学习-迁移学习到的知识-在模型的训练方式上带来了一个范式的转变。提高准确性和减少训练时间的利润丰厚的好处已经在具有有限计算资源和较少训练样本的训练模型中显示出了希望。具体而言,在大型数据集语料库上训练的公开可用的基于文本的模型,如GloVe和BERT,在实践中已经得到了普遍采用。在本文中,我们问,“可以利用文本预测模型中的迁移学习来执行误分类攻击吗?“作为我们的主要贡献,我们提出了新的攻击技术,利用教师(公共)模型中学习到的非预期特征为学生(下游)模型生成对抗性示例。据我们所知,我们的工作是第一次表明,迁移学习从国家的最先进的字为基础的教师模型,并以学生为基础的模型增加的敏感性错误分类攻击。首先,我们提出了一种新的基于单词分数的攻击算法,用于生成对抗使用上下文无关的单词级嵌入模型训练的学生模型的示例。在使用GloVe教师模型训练的二进制分类任务中,我们对IMDB电影评论的平均攻击准确率为97%,对假新闻检测的平均攻击准确率为80%。对于多类任务,我们将新闻组数据集分为6类和20类,平均攻击准确率分别为75%和41%。接下来,我们针对使用上下文感知BERT模型训练的假新闻检测任务,提出了基于长度和基于时间的错误分类攻击,分别达到了78%和39%的攻击准确率。因此,我们的研究结果激发了设计训练技术的需求,这些技术对非预期的特征学习具有鲁棒性,特别是对于迁移学习模型。

英文摘要:

Transfer learning --- transferring learned knowledge --- has brought a paradigm shift in the way models are trained. The lucrative benefits of improved accuracy and reduced training time have shown promise in training models with constrained computational resources and fewer training samples. Specifically, publicly available text-based models such as GloVe and BERT that are trained on large corpus of datasets have seen ubiquitous adoption in practice. In this paper, we ask, "can transfer learning in text prediction models be exploited to perform misclassification attacks?" As our main contribution, we present novel attack techniques that utilize unintended features learnt in the teacher (public) model to generate adversarial examples for student (downstream) models. To the best of our knowledge, ours is the first work to show that transfer learning from state-of-the-art word-based and sentence-based teacher models increase the susceptibility of student models to misclassification attacks. First, we propose a novel word-score based attack algorithm for generating adversarial examples against student models trained using context-free word-level embedding model. On binary classification tasks trained using the GloVe teacher model, we achieve an average attack accuracy of 97% for the IMDB Movie Reviews and 80% for the Fake News Detection. For multi-class tasks, we divide the Newsgroup dataset into 6 and 20 classes and achieve an average attack accuracy of 75% and 41% respectively. Next, we present length-based and sentence-based misclassification attacks for the Fake News Detection task trained using a context-aware BERT model and achieve 78% and 39% attack accuracy respectively. Thus, our results motivate the need for designing training techniques that are robust to unintended feature learning, specifically for transfer learned models.

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。

↑