2 papers
cs.CR2026
Implementing a White-Box Undetectable Backdoor for Random Fourier Features
Michael Collins, Jada Cumberland, Brianne Dunn +3
Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorithm, under a hardness assumption…
cs.CR2026
Weird Machines in Transport Layer Security
Michael Collins, Jada Cumberland, Brianne Dunn +4
Weird machines are latent computational capabilities that emerge from the composition of architectural components. Prior work has studied this phenomenon extensively in software sy…