How vinairesearch/anti-dreambooth works
Anti-DreamBooth protects personal photos by generating subtle adversarial perturbations intended to weaken DreamBooth personalization; users can also train and run DreamBooth models and evaluate generated images. The graph keeps the documented attack, training, inference, and evaluation branches distinct. Edges are limited to README-documented workflows and relationships visible in the supplied excerpts or SOURCE INDEX; some evaluation entry points and attack implementations were not sampled.
Main entry points: DeepFace.py Face evaluation · face_image_quality.py SER-FIQ scoring · ism_fdfr.py Identity scores · train_dreambooth.py DreamBooth training
Components 29
Image defense
- ASPL attack
attacks/aspl.py - ASPL LoRA
attacks/aspl_lora.py - Ensemble ASPL
attacks/ensemble_aspl.py - FSMG attack
attacks/fsmg.py - Ensemble FSMG
attacks/ensemble_fsmg.py - Perturbed images
DreamBooth generation
- DreamBooth training
train_dreambooth.py - LoRA training
train_dreambooth_lora.py - Trained model
- Image inference
infer.py - Generated images
Face identity analysis
- Face evaluation
evaluations/deepface/deepface/DeepFace.py - Face API routes
evaluations/deepface/api/routes.py - Face API service
evaluations/deepface/api/service.py - Face preprocessing
evaluations/deepface/deepface/commons/functions.py - Face detectors
evaluations/deepface/deepface/detectors/FaceDetector.py - Embedding backbones
evaluations/deepface/deepface/basemodels/Facenet.py - Attribute models
evaluations/deepface/deepface/extendedmodels/Emotion.py - Distance metrics
evaluations/deepface/deepface/commons/distance.py - Index embeddings
evaluations/compute_idx_emb.py - Identity scores
evaluations/ism_fdfr.py
Image quality analysis
- SER-FIQ scoring
evaluations/FaceImageQuality/face_image_quality.py - MTCNN detection
evaluations/FaceImageQuality/insightface/src/mtcnn_detector.py - Face alignment
evaluations/FaceImageQuality/insightface/src/face_preprocess.py - BRISQUE scoring
evaluations/brisques.py - RetinaFace detection
evaluations/retinaface/retinaface/RetinaFace.py - RetinaFace model
evaluations/retinaface/retinaface/model/retinaface_model.py - RetinaFace postprocess
evaluations/retinaface/retinaface/commons/postprocess.py
Other components
- User
Connections 37
- User → ASPL attack: selects defense
- User → ASPL LoRA: selects defense
- User → Ensemble ASPL: selects defense
- User → FSMG attack: selects defense
- User → Ensemble FSMG: selects defense
- ASPL attack → Perturbed images: perturbs images
- ASPL LoRA → Perturbed images: perturbs images
- Ensemble ASPL → Perturbed images: perturbs images
- FSMG attack → Perturbed images: perturbs images
- Ensemble FSMG → Perturbed images: perturbs images
- User → DreamBooth training: provides images
- User → LoRA training: provides images
- Perturbed images → DreamBooth training: trains on
- Perturbed images → LoRA training: trains on
- DreamBooth training → Trained model: trains
- LoRA training → Trained model: trains
- User → Image inference: requests generation
- Trained model → Image inference: loads model
- Image inference → Generated images: generates
- Face API routes → Face API service: routes requests
evaluations/deepface/api/routes.py - Face API service → Face evaluation: calls analysis
evaluations/deepface/api/service.py - Face evaluation → Face preprocessing: extracts faces
evaluations/deepface/deepface/DeepFace.py - Face preprocessing → Face detectors: dispatches detection
evaluations/deepface/deepface/commons/functions.py - Face evaluation → Embedding backbones: selects backbones
evaluations/deepface/deepface/DeepFace.py - Face evaluation → Attribute models: loads attributes
evaluations/deepface/deepface/DeepFace.py - Face evaluation → Distance metrics: uses metrics
evaluations/deepface/deepface/DeepFace.py - Index embeddings → Face evaluation: extracts embeddings
evaluations/compute_idx_emb.py - Identity scores → Face evaluation: extracts embeddings
evaluations/ism_fdfr.py - Identity scores → Index embeddings: loads reference embedding
evaluations/ism_fdfr.py - SER-FIQ scoring → MTCNN detection: detects faces
evaluations/FaceImageQuality/face_image_quality.py - SER-FIQ scoring → Face alignment: aligns faces
evaluations/FaceImageQuality/face_image_quality.py - RetinaFace detection → RetinaFace model: builds model
evaluations/retinaface/retinaface/RetinaFace.py - RetinaFace detection → RetinaFace postprocess: processes detections
evaluations/retinaface/retinaface/RetinaFace.py - User → SER-FIQ scoring: evaluates images
- User → BRISQUE scoring: evaluates images
- Generated images → Identity scores: measures identity
- Generated images → SER-FIQ scoring: measures quality