A bibliometric study toward quantitative research assessment of security of machine learning
Purpose Advances in machine learning (ML) have made significant contributions to the
development of intelligent and autonomous systems leading to concerns about resilience of …
development of intelligent and autonomous systems leading to concerns about resilience of …
Understanding Implosion in Text-to-Image Generative Models
Recent works show that text-to-image generative models are surprisingly vulnerable to a
variety of poisoning attacks. Empirical results find that these models can be corrupted by …
variety of poisoning attacks. Empirical results find that these models can be corrupted by …
Disguised Copyright Infringement of Latent Diffusion Model
Copyright infringement may occur when a generative model produces samples substantially
similar to some copyrighted data that it had access to during the training phase. The notion …
similar to some copyrighted data that it had access to during the training phase. The notion …