New Study Shows Bayesian Inference Can Be Manipulated Through Data Poisoning
A new arXiv paper examines how adversarial data poisoning can steer Bayesian inference and the decisions that follow from it, extending known model-manipulation risks to Bayesian statistical methods.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv stat.ML
Steering Bayesian Inference and Decisions through Data Poisoning