SynGhost：通过句法迁移实现隐形且通用的任务无关后门攻击
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
AI总结：
本文提出SynGhost，一种通过句法迁移实现的隐形通用任务无关后门攻击，利用对比学习选择目标并引入感知模块，能有效迁移至下游任务并抵抗多种防御。
摘要：
尽管预训练取得了显著性能，但由于数据和训练机制中的漏洞，它容易受到任务无关的后门攻击。这些攻击可以将后门迁移到各种下游任务中。在本文中，我们引入了maxEntropy，一种基于熵的投毒过滤器，以缓解此类风险。为了克服手动目标设置和显式触发器的局限性，我们提出了SynGhost，一种通过句法迁移实现的隐形且通用的任务无关后门攻击，进一步暴露了预训练语言模型（PLMs）中的漏洞。具体来说，SynGhost通过语料投毒将多个句法后门注入预训练空间，同时保持PLM的预训练能力。其次，SynGhost基于对比学习自适应地选择最优目标，在预训练空间中创建均匀分布。为了识别句法差异，我们还引入了一个感知模块以最小化后门之间的干扰。实验表明，SynGhost构成显著威胁，并能迁移到各种下游任务。此外，SynGhost能够抵抗基于困惑度、微调和maxEntropy的防御。代码可在该https URL获取。
英文摘要：
Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper, we introduce $\mathtt{maxEntropy}$, an entropy-based poisoning filter that mitigates such risks. To overcome the limitations of manual target setting and explicit triggers, we propose $\mathtt{SynGhost}$, an invisible and universal task-agnostic backdoor attack via syntactic transfer, further exposing vulnerabilities in pre-trained language models (PLMs). Specifically, $\mathtt{SynGhost}$ injects multiple syntactic backdoors into the pre-training space through corpus poisoning, while preserving the PLM's pre-training capabilities. Second, $\mathtt{SynGhost}$ adaptively selects optimal targets based on contrastive learning, creating a uniform distribution in the pre-training space. To identify syntactic differences, we also introduce an awareness module to minimize interference between backdoors. Experiments show that $\mathtt{SynGhost}$ poses significant threats and can transfer to various downstream tasks. Furthermore, $\mathtt{SynGhost}$ resists defenses based on perplexity, fine-pruning, and $\mathtt{maxEntropy}$. The code is available at https://github.com/Zhou-CyberSecurity-AI/SynGhost.
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。
