PromptFix：通过对抗性提示调优实现少样本后门移除
PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning
AI总结：
本文提出PromptFix，一种少样本场景下通过对抗性提示调优移除NLP模型后门的方法，保持模型参数不变，仅用两组软令牌近似并抵消触发词，在多种攻击和领域偏移下验证了有效性。
摘要：
预训练语言模型（PLMs）在过去几年中凭借其无与伦比的性能吸引了大量关注。与此同时，训练PLMs的高昂成本及其出色的泛化能力共同推动了少样本微调和提示成为自然语言处理（NLP）模型最流行的训练范式。然而，现有研究表明，这些NLP模型可能被植入后门，从而在出现触发词时操纵模型行为。在本文中，我们提出了PromptFix，这是一种在少样本场景下通过对抗性提示调优为NLP模型设计的全新后门缓解策略。与现有依赖精确触发反演和后续模型微调的NLP后门移除方法不同，PromptFix保持模型参数不变，仅利用两组额外的软令牌，分别近似触发词并对其进行抵消。软令牌和对抗性优化的使用消除了枚举可能后门配置的需要，并能在触发词发现与性能保持之间实现自适应平衡。针对多种后门攻击的实验验证了所提方法的有效性，而在存在领域偏移时的性能进一步表明PromptFix适用于在未知数据源上预训练的模型，这是提示调优场景中的常见情况。
英文摘要：
Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed to few-shot fine-tuning and prompting as the most popular training paradigms for natural language processing (NLP) models. Nevertheless, existing studies have shown that these NLP models can be backdoored such that model behavior is manipulated when trigger tokens are presented. In this paper, we propose PromptFix, a novel backdoor mitigation strategy for NLP models via adversarial prompt-tuning in few-shot settings. Unlike existing NLP backdoor removal methods, which rely on accurate trigger inversion and subsequent model fine-tuning, PromptFix keeps the model parameters intact and only utilizes two extra sets of soft tokens which approximate the trigger and counteract it respectively. The use of soft tokens and adversarial optimization eliminates the need to enumerate possible backdoor configurations and enables an adaptive balance between trigger finding and preservation of performance. Experiments with various backdoor attacks validate the effectiveness of the proposed method and the performances when domain shift is present further shows PromptFix's applicability to models pretrained on unknown data source which is the common case in prompt tuning scenarios.
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。
