Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models

ArXi:2502.20650v5 Announce Type: replace Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses, such as backdoor detection and trigger inversion, are largely effective because prior attacks rely on limited input spaces and low-dimensional triggers that are visually conspicuous or easily captured by neural detectors.