Parameter-efficient fine-tuning (PEFT) enables efficient adaptation of pre-trained language models (PLMs) to specific tasks. By tuning only a minimal set of (extra) parameters, PEFT achieves performance that is comparable to standard fine-tuning. However, despite its prevalent use, the security implications of PEFT remain largely unexplored. In this paper, we take the initial steps and present PETA, a novel trojan attack that compromises the weights of PLMs by accounting for downstream adaptation through bilevel optimization: the upper-level objective embeds the backdoor into a model while the lower-level objective simulates PEFT to both retain the PLM's task-specific performance and ensure that the backdoor persists after fine-tuning. With extensive evaluation across a variety of downstream tasks and trigger designs, we demonstrate PETA's effectiveness in terms of both attack success rate and clean accuracy, even when the attacker does not have full knowledge of the victim user's training process.

翻译：参数高效微调（PEFT）能够将预训练语言模型（PLM）高效适配到特定任务。仅需调整极少量（额外）参数，PEFT即可达到与标准微调相当的性能。然而，尽管其应用广泛，PEFT的安全影响尚未得到充分研究。本文迈出探索性第一步，提出新型后门攻击方法PETA，通过双层优化破坏PLM的权重：上层目标将后门植入模型，下层目标模拟PEFT以保持PLM的任务性能并确保后门在微调后持续存在。通过在多种下游任务和触发机制设计上的广泛评估，我们证明了PETA在攻击成功率和干净准确率方面的有效性，即使攻击者无法完全掌握受害者用户的训练过程。