Tootfinder

Golden Partition Zone: Rethinking Neural Network Partitioning Under Inversion Threats in Collaborative Inference
Rongke Liu, Youwen Zhu
https://arxiv.org/abs/2506.15412

Golden Partition Zone: Rethinking Neural Network Partitioning Under Inversion Threats in Collaborative Inference
In collaborative inference, intermediate features transmitted from edge devices can be exploited by adversaries to reconstruct original inputs via model inversion attacks (MIA). While existing defenses focus on shallow-layer protection, they often incur significant utility loss. A key open question is how to partition the edge-cloud model to maximize resistance to MIA while minimizing accuracy degradation. We first show that increasing model depth alone does not guarantee resistance. Through th…

This https://arxiv.org/abs/2505.18715 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_…

Cloud and Haze Parameterization in Atmospheric Retrievals: Insights from Titan's Cassini Data and JWST Observations of Hot Jupiters
Context: Before JWST, telescope observations were not sensitive enough to constrain the nature of clouds in exo-atmospheres. Recent observations, however, have inferred cloud signatures as well as haze-enhanced scattering slopes motivating the need for modern inversion techniques and a deeper understanding of the JWST information content. Aims: We aim to investigate the information content of JWST exoplanet spectra. We particularly focus on designing an inversion technique able to handle a wi…