arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.27465q-bio.GN
收藏

基因组投毒:针对DNA基础模型的目标后门攻击

Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models

The University of Texas at Austin(德克萨斯大学奥斯汀分校);Dell Pediatric Research Institute(戴尔儿科研究所)

Charalampos Koilakos, Ioannis Mouratidis, Ilias Georgakopoulos-Soares

AI总结:

本研究首次系统研究基因组语言模型的训练数据投毒,通过在预训练和微调阶段注入少于1%的对抗序列,可选择性破坏目标基因组上下文的生成性能,并实现条件后门攻击和下游任务分类破坏。

摘要:

基于DNA序列训练的基础模型在变异效应预测和基因组设计等生物学任务中取得了强劲性能。这些模型依赖于包含数万亿核苷酸标记的大规模公共基因组数据集。与自然语言不同,DNA序列缺乏语义透明性,使得在数据整理过程中难以检测被破坏或对抗性构造的条目。我们首次系统研究了基因组语言模型中的训练数据投毒,针对预训练和微调阶段。在预训练中,使用Evo 2和GENERator架构,我们表明训练语料中少于1%的对抗性构造序列可以选择性地降低目标基因组上下文上的生成性能,同时不影响无关序列。我们评估了三种场景:TATA-box启动子基序的破坏、CTCF结合位点的干扰以及插入所有训练基因组中不存在的合成序列。在微调中,我们展示了另外两种攻击。首先,在ClinVar衍生语料库中投毒一部分CTCF位点,在LoRA适配模型中安装一个条件后门,该后门几乎仅在触发序列存在时激活。其次,使用冻结的Evo 2 7B嵌入,对下游训练数据进行目标标签破坏,选择性地损害临床相关的变异分类任务,在BRCA1变异效应预测上进行了演示。这些结果表明基因组基础模型容易受到最小足迹的目标数据投毒。我们敦促该领域将数据来源追踪、完整性验证和对抗鲁棒性评估作为基因组模型开发管道的标准组成部分。

英文摘要:

Foundation models trained on DNA sequences have achieved strong performance across biological tasks including variant effect prediction and genome design. These models rely on massive public genomic datasets comprising trillions of nucleotide tokens. Unlike natural language, DNA sequences lack semantic transparency, making corrupted or adversarially crafted entries difficult to detect during data curation. We present the first systematic study of training data poisoning in genomic language models, targeting both pre-training and fine-tuning stages. At pre-training, using Evo 2 and GENERator architectures, we show that less than 1% adversarially crafted sequences in the training corpus can selectively degrade generative performance on targeted genomic contexts while leaving unrelated sequences unaffected. We evaluate three scenarios: corruption of TATA-box promoter motifs, disruption of CTCF binding sites, and insertion of synthetic sequences absent from all training genomes. At fine-tuning, we demonstrate two additional attacks. First, poisoning a subset of CTCF sites in a ClinVar-derived corpus installs a conditional backdoor in a LoRA-adapted model that activates almost exclusively when the trigger sequence is present. Second, using frozen Evo 2 7B embeddings, targeted label corruption of downstream training data selectively compromises a clinically relevant variant classification task, demonstrated on BRCA1 variant effect prediction. These results show genomic foundation models are susceptible to targeted data poisoning with minimal footprint. We urge the field to adopt data provenance tracking, integrity verification, and adversarial robustness evaluation as standard components of the genomic model development pipeline.

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。

↑