Search papers, labs, and topics across Lattice.
3
0
5
6
RAPID is proposed, a self-referenced latent maximization framework that removes external dependencies and encourages the same model update to induce consistently disruptive effects across training samples, thereby improving reachability and establishing a paradigm for real-time protection against unauthorized distillation in deployed T2I systems.
Backdoor attacks can be stealthily inherited during model merging, but DiffSafeMerge ensures zero worst-target ASR while preserving image quality across multiple datasets.
InkShield reduces the risk of handwriting forgery by over 90% while keeping the original style visually intact.
