Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models

Charalampos Koilakos, Ioannis Mouratidis, Ilias Georgakopoulos-Soares

Abstract

Genomic foundation models trained on DNA sequences have demonstrated remarkable capabilities across diverse biological tasks, from variant effect prediction to genome design. These models are typically trained on massive, publicly sourced genomic datasets comprising trillions of nucleotide tokens, which renders them intrinsically susceptible to errors, artifacts, and adversarial issues embedded in the training data. Unlike natural language, DNA sequences lack the semantic transparency that might

Categories

Cite This Resource

@article{llmsec202600158,
  title = {Poisoning the Genome: Targeted Backdoor Attacks on DNA Foundation Models},
  author = {Charalampos Koilakos and Ioannis Mouratidis and Ilias Georgakopoulos-Soares},
  year = {2026},
  url = {https://arxiv.org/abs/2603.27465},
}