Conjunctive Poisoning in AI Supply-Chain Applications

Abstract

Large Language and Vision-Language Models are increasingly deployed through inference pipelines that include prompt wrappers (e.g., templates and post-processing scripts) and configuration metadata (e.g., JSON/YAML files) that together shape model outputs. While model weights and binaries are routinely verified, these textual deployment artifacts remain weakly protected despite directly influencing runtime behavior. We show that a malicious developer can pair a benign-looking wrapper with crafte

Categories

Framework mappings

Suggested from the entry's categories.

@misc{arif2026conjunctiveb,
  title = {{Conjunctive Poisoning in AI Supply-Chain Applications}},
  author = {Nokimul Hasan Arif and Qian Lou and Meng Zheng},
  year = {2026},
  month = aug,
  eprint = {2608.15913},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/d9175f51a25b86b6c86fb663397e860b28b80933}
}