Indirect Data Poisoning Could Enable Large-Scale Scientific Fraud via AI Agents

Jul 14, 2026

A new preprint demonstrates that adversaries can corrupt open datasets to poison AI-driven scientific research, with attacks succeeding in nearly half of experimental runs and detection rates remaining very low. The attack leverages autonomous research agents that retrieve and process public data, potentially turning well-intentioned scientists into unwitting distributors of fraudulent results. The study also finds that implementing provenance auditing with five specific checks can reduce attack success to zero.

Why it matters: This research exposes a scalable vulnerability in AI-assisted science that could industrialize scientific fraud, posing a significant threat to the integrity of research in critical domains.

Full story at: arXiv Cryptography and Security ↗