REVIEW 5 cited by
Membership Inference of 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
Recent years have witnessed the tremendous success of diffusion models in data synthesis. However, when diffusion models are applied to sensitive data, they also give rise to severe privacy concerns. In this paper, we systematically present the first study about membership inference attacks against diffusion models, which aims to infer whether a sample was used to train the model. Two attack methods are proposed, namely loss-based and likelihood-based attacks. Our attack methods are evaluated on several state-of-the-art diffusion models, over different datasets in relation to privacy-sensitive data. Extensive experimental evaluations show that our attacks can achieve remarkable performance. Furthermore, we exhaustively investigate various factors which can affect attack performance. Finally, we also evaluate the performance of our attack methods on diffusion models trained with differential privacy.
Forward citations
Cited by 5 Pith papers
-
SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation
A systematic survey and benchmark showing that diffusion-based synthetic data can achieve better utility-privacy tradeoffs than DP-SGD on real data for some image classifiers, with the best release strategy depending ...
-
IDDM: Identity-Decoupled Personalized Diffusion Models with a Tunable Privacy-Utility Trade-off
IDDM immunizes authorized personalized diffusion models so public generations remain high-quality while identity linkability to face recognizers is reduced with a tunable privacy-utility knob.
-
NAMESAKES: Probing Identity Memorization in Text-to-Image Models
A two-signal probe — generation consistency and centroid distinctiveness — separates memorized from fabricated identities in black-box text-to-image models, tested on the new NAMESAKES benchmark.
-
Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
In overparameterized diffusion models, generalization happens first and memorization starts later, with the memorization time growing linearly with dataset size.
-
Memory Enhanced Fractional-Order Dung Beetle Optimization for Photovoltaic Parameter Identification
The claimed MFO-DBO algorithm and its CEC2017/PV results are absent from the manuscript, which instead contains an unrelated prompt-stealing attack paper.
Discussion (0). Sign in to comment.