Is AI Robust Enough for Scientific Research?
This highlights a reliability and security problem for scientists and researchers relying on AI, indicating an incremental concern rather than a new solution.
The paper reveals that neural networks are highly vulnerable to small perturbations, causing significant output deviations across five scientific domains, exposing a hidden risk in using AI for critical scientific computations.
We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five diverse application areas -- weather forecasting, chemical energy and force calculations, fluid dynamics, quantum chromodynamics, and wireless communication -- we demonstrate that this vulnerability is a broad and general characteristic of AI systems. This revelation exposes a hidden risk in relying on neural networks for essential scientific computations, calling further studies on their reliability and security.