对比产生的捷径:基于提示的学习中有效且隐蔽的干净标签攻击
Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
AI总结:
本文针对基于提示学习中干净标签后门攻击难以兼顾有效性与隐蔽性的问题,提出对比捷径注入(CSI)方法,利用激活值整合触发器设计与数据选择,在低投毒率下实现高有效性和高隐蔽性攻击。
摘要:
基于提示的学习范式在增强预训练语言模型(PLMs)的适应性方面展现出显著效果,尤其是在少样本场景中。然而,这种学习范式已被证明容易受到后门攻击。当前的干净标签攻击采用特定提示作为触发器,无需外部触发器即可成功实施,并确保中毒样本的标签正确,与中毒标签攻击相比更具隐蔽性,但另一方面,它面临严重的误激活问题,并带来更大挑战,需要更高的投毒率。通过使用常规的负数据增强方法,我们发现在干净标签设置下很难在有效性和隐蔽性之间取得平衡。为解决这一问题,我们受到后门充当捷径这一概念的启发,并假设该捷径源于触发器与用于投毒的数据之间的对比。在本研究中,我们提出了一种名为对比捷径注入(CSI)的方法,通过利用激活值,整合触发器设计和数据选择策略来构建更强的捷径特征。通过在全文和少样本文本分类任务上进行大量实验,我们实证验证了CSI在低投毒率下的高有效性和高隐蔽性。值得注意的是,我们发现这两种方法分别在全文和少样本设置中起主导作用。
英文摘要:
Prompt-based learning paradigm has demonstrated remarkable efficacy in enhancing the adaptability of pretrained language models (PLMs), particularly in few-shot scenarios. However, this learning paradigm has been shown to be vulnerable to backdoor attacks. The current clean-label attack, employing a specific prompt as a trigger, can achieve success without the need for external triggers and ensure correct labeling of poisoned samples, which is more stealthy compared to the poisoned-label attack, but on the other hand, it faces significant issues with false activations and poses greater challenges, necessitating a higher rate of poisoning. Using conventional negative data augmentation methods, we discovered that it is challenging to trade off between effectiveness and stealthiness in a clean-label setting. In addressing this issue, we are inspired by the notion that a backdoor acts as a shortcut and posit that this shortcut stems from the contrast between the trigger and the data utilized for poisoning. In this study, we propose a method named Contrastive Shortcut Injection (CSI), by leveraging activation values, integrates trigger design and data selection strategies to craft stronger shortcut features. With extensive experiments on full-shot and few-shot text classification tasks, we empirically validate CSI's high effectiveness and high stealthiness at low poisoning rates. Notably, we found that the two approaches play leading roles in full-shot and few-shot settings, respectively.
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。