SMAB:基于MAB的单词敏感度估计框架及其在对抗性文本生成中的应用
SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation
AI总结:
针对现有序列分类敏感度计算因指数复杂度难以大规模应用的问题,提出SMAB框架以可扩展方式计算单词级局部和全局敏感度,通过多任务实验验证其作为准确率代理指标的有效性,并在对抗性文本生成中提升攻击成功率和复述性能。
摘要:
为理解序列分类任务的复杂性,Hahn等人(2021)提出敏感度概念,即输入序列中可单独修改以改变输出的不相交子集数量。尽管该框架有效,但因其指数时间复杂度,大规模计算敏感度成本高昂。因此,我们引入基于敏感度的多臂老虎机框架(SMAB),为任意数据集提供可扩展方法,用于计算文本分类器下单词级别的局部(句子级)和全局(聚合)敏感度。我们通过多种应用验证方法有效性:在CHECKLIST生成的情感分析数据集上开展案例研究,表明算法能捕捉直觉上高敏感和低敏感的单词;在多任务和多语言场景下进行实验,证明敏感度可在无黄金数据时作为准确率的代理指标;最后,在对抗性示例生成中利用敏感度值引导扰动提示,使攻击成功率提升15.58%,而在对抗性复述生成中以敏感度作为额外奖励,比现有SOTA方法提升12.00%。警告:包含潜在冒犯性内容。
英文摘要:
To understand the complexity of sequence classification tasks, Hahn et al. (2021) proposed sensitivity as the number of disjoint subsets of the input sequence that can each be individually changed to change the output. Though effective, calculating sensitivity at scale using this framework is costly because of exponential time complexity. Therefore, we introduce a Sensitivity-based Multi-Armed Bandit framework (SMAB), which provides a scalable approach for calculating word-level local (sentence-level) and global (aggregated) sensitivities concerning an underlying text classifier for any dataset. We establish the effectiveness of our approach through various applications. We perform a case study on CHECKLIST generated sentiment analysis dataset where we show that our algorithm indeed captures intuitively high and low-sensitive words. Through experiments on multiple tasks and languages, we show that sensitivity can serve as a proxy for accuracy in the absence of gold data. Lastly, we show that guiding perturbation prompts using sensitivity values in adversarial example generation improves attack success rate by 15.58%, whereas using sensitivity as an additional reward in adversarial paraphrase generation gives a 12.00% improvement over SOTA approaches. Warning: Contains potentially offensive content.
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。