REVIEW 7 cited by
Extracting Training Data from Diffusion Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Image diffusion models such as DALL-E 2, Imagen, and Stable Diffusion have attracted significant attention due to their ability to generate high-quality synthetic images. In this work, we show that diffusion models memorize individual images from their training data and emit them at generation time. With a generate-and-filter pipeline, we extract over a thousand training examples from state-of-the-art models, ranging from photographs of individual people to trademarked company logos. We also train hundreds of diffusion models in various settings to analyze how different modeling and data decisions affect privacy. Overall, our results show that diffusion models are much less private than prior generative models such as GANs, and that mitigating these vulnerabilities may require new advances in privacy-preserving training.
Forward citations
Cited by 7 Pith papers
-
The Space Complexity of Learning-Unlearning Algorithms
The space complexity of machine unlearning for realizability testing is characterized by eluder dimension (central lower bound), star number (ticketed upper bound), and hollow star number (bounded deletions), separati...
-
GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning
GUDA approximates leave-one-group-out counterfactual models with unlearning and ranks group influence by ELBO differences.
-
How much do language models memorize?
A compression-based measurement puts GPT-style model memorization capacity at roughly 3.6 bits per parameter, with membership inference success following a sigmoid in the dataset-to-capacity ratio.
-
Benchmark Leakage Trap: Can We Trust LLM-based Recommendation?
Fine-tuning an LLM recommender on a slice of the benchmark inflates AUC/UAUC for in-domain leakage and degrades it for out-of-domain leakage, showing benchmark contamination can distort LLM-based recommendation evaluation.
-
Low-Perplexity LLM-Generated Sequences and Where To Find Them
Only about 40% of low-perplexity 6-token spans generated by Pythia-6.9B can be exactly matched to The Pile, and the authors categorize matched and unmatched spans into four classes.
-
Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
Sparse autoencoders and ITDA produce comparably interpretable and steerable features in FLUX.1, outperforming MLP neurons on an automated visual interpretability metric.
-
SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing
SPARK is a proposed framework that coordinates persona-based LLM agents with layered memory and three collaboration protocols to produce personalized search.
Discussion (0). Continue with ORCID to comment.