Plausible Adversarial Attacks on Direct Parameter Inference Models in Astrophysics [CEA]

http://arxiv.org/abs/2211.14788


In this abstract we explore the possibility of introducing biases in physical parameter inference 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.

Read this paper on arXiv…

B. Horowitz and P. Melchior
Tue, 29 Nov 22
65/80

Comments: Accepted submission to Machine Learning and the Physical Sciences workshop, NeurIPS 2022