Plausible Adversarial Attacks on Direct Parameter Inference Models in Astrophysics

In this work we explore the possibility of introducing biases in physical parameterinference models from adversarial-type attacks. In particular, we inject small amplitude systematics into inputs to a mixture density networks tasked with inferring cosmological parameters from observed data. The systematics are constructed analogously to white-box adversarial attacks. We find that the analysis network can be tricked into spurious detection of new physics in cases where standard cosmological estimators would be insensitive. This calls into question the robustness of such networks and their utility for reliably detecting new physics.