AI RESEARCH
TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models
arXiv CS.CV
•
ArXi:2603.17828v1 Announce Type: new Although text-to-image diffusion models exhibit remarkable generative power, concept erasure techniques are essential for their safe deployment to prevent the creation of harmful content. This has fostered a dynamic interplay between the development of erasure defenses and the adversarial probes designed to bypass them, and this co-evolution has progressively enhanced the efficacy of erasure methods.