Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Removing Watermarks with Partial Regeneration using Semantic Information
Krti Tallam, John Kevin Cava, Caleb Geniesse +2
As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed seman…
cs.LG2025
Loss Landscape Analysis for Reliable Quantized ML Models for Scientific Sensing
Tommaso Baldi, Javier Campos, Olivia Weng +4
In this paper, we propose a method to perform empirical analysis of the loss landscape of machine learning (ML) models. The method is applied to two ML models for scientific sensin…