How do you poison an agent that learns skills? Hijack the experience-to-skill pipeline and make the backdoor stick.
trending2
01 02 Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor arxiv.orgPaper shows a stealthy backdoored VAE encoder can make diffusion semantic watermarks disappear, which is a fun failure mode.