Hydra stabilizes multi-concept backdoor attacks in diffusion models via evolutionary trigger search in text encoder space and trigger-clean regularization during multi-task fine-tuning, achieving high attack success while preserving clean image quality.
arXiv preprint arXiv:2302.07944 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6verdicts
UNVERDICTED 6representative citing papers
DADD disentangles anatomy and disease in a latent diffusion model using a Feature Purifier, ordinal disease embeddings, and Delta Steering to synthesize controllable ulcerative colitis progression images.
AC3S adds a self-supervised visual prompt modulator to ControlNet diffusion and a multi-agent VLM prompt composer to generate photorealistic images with accurate 2D/3D annotations while avoiding over-conditioning.
DecoupleGen personalizes diffusion models to create images with uncommon contexts for debiasing object recognition, yielding consistent gains on scene classification tasks.
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
Analysis of MTS reveals poor GSNR and uninformative features; larger batches and distribution-based features yield 5.49% and 2.89% gains on benchmarks.
citing papers explorer
-
Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
Hydra stabilizes multi-concept backdoor attacks in diffusion models via evolutionary trigger search in text encoder space and trigger-clean regularization during multi-task fine-tuning, achieving high attack success while preserving clean image quality.
-
Disentangled Anatomy-Disease Diffusion (DADD) for Controllable Ulcerative Colitis Progression Synthesis
DADD disentangles anatomy and disease in a latent diffusion model using a Feature Purifier, ordinal disease embeddings, and Delta Steering to synthesize controllable ulcerative colitis progression images.
-
AC3S: Adaptive Conditioning for 3D-Aware Synthetic Data Generation
AC3S adds a self-supervised visual prompt modulator to ControlNet diffusion and a multi-agent VLM prompt composer to generate photorealistic images with accurate 2D/3D annotations while avoiding over-conditioning.
-
Personalized Generative Models for Contextual Debiasing
DecoupleGen personalizes diffusion models to create images with uncommon contexts for debiasing object recognition, yielding consistent gains on scene classification tasks.
-
Mutual Enhancement Between Global Tokens and Patch Tokens: From Theory to Practice
TaTok is a theoretically grounded adaptive tokenization method that uses global tokens and cumulative conditional entropy filtering to reduce redundancy while improving reconstruction quality over fixed-rate patch tokenization.
-
On the Difficulty of Learning a Meta-network for Training Data Selection
Analysis of MTS reveals poor GSNR and uninformative features; larger batches and distribution-based features yield 5.49% and 2.89% gains on benchmarks.