Papers › Are Diffusion Models Vulnerable to Membership Inference Attacks?

Are Diffusion Models Vulnerable to Membership Inference Attacks?

2 Feb 2023arXiv:2302.01316archive 2025-07-28

Jinhao Duan, Fei Kong, Shiqi Wang, Xiaoshuang Shi, Kaidi Xu

Diffusion-based generative models have shown great potential for image synthesis, but there is a lack of research on the security and privacy risks they may pose. In this paper, we investigate the vulnerability of diffusion models to Membership Inference Attacks (MIAs), a common privacy concern. Our results indicate that existing MIAs designed for GANs or VAE are largely ineffective on diffusion models, either due to inapplicable scenarios (e.g., requiring the discriminator of GANs) or inappropriate assumptions (e.g., closer distances between synthetic samples and member samples). To address this gap, we propose Step-wise Error Comparing Membership Inference (SecMI), a query-based MIA that infers memberships by assessing the matching of forward process posterior estimation at each timestep. SecMI follows the common overfitting assumption in MIA where member samples normally have smaller estimation errors, compared with hold-out samples. We consider both the standard diffusion models, e.g., DDPM, and the text-to-image diffusion models, e.g., Latent Diffusion Models and Stable Diffusion. Experimental results demonstrate that our methods precisely infer the membership with high confidence on both of the two scenarios across multiple different datasets. Code is available at https://github.com/jinhaoduan/SecMI.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2302.01316")

Code

Syntology Ran 11 of 23 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 8 ran with no contract checked.

By repository: official repository: 22 samples from 1 repository, 11 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jinhaoduan/secmi officialmentioned in papermentioned on GitHubpytorchMIT report
jinhaoduan/SecMI-LDM mentioned on GitHubjax report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested; 11 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
1ran · fixture could not drive it
8ran
12unverified

Licence: 0 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

MIDataset jinhaoduan/secmi/mia_evals/secmia.py official repository ran fingerprinted MIT (permissive) · d36d04cf36d3999f · report
ResNet jinhaoduan/secmi/mia_evals/secmia.py official repository ran · metamorphic tier: invariant MIT (permissive) · 23f4defe80b11a2d · report
ResNet18 jinhaoduan/secmi/mia_evals/secmia.py official repository ran · fixture could not drive it MIT (permissive) · eba347d140a27299 · report
ddim_multistep jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · 8875f269d4f25f54 · report
ddim_singlestep jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · 8aae53c2358ad7f0 · report
get_intermediate_results jinhaoduan/secmi/mia_evals/secmia.py official repository ran · our draft was wrong MIT (permissive) · be9ea01d28064f30 · report
naive_statistic_attack jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · 7f5852ef1a8b8ff1 · report
nn_eval jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · 2329c33cd9385b7f · report
nn_train jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · 94c0240d193981e4 · report
roc jinhaoduan/secmi/mia_evals/secmia.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · a1c7d50f62f751e4 · report
split_nn_datasets jinhaoduan/secmi/mia_evals/secmia.py official repository ran MIT (permissive) · f875a34ca4b25fe9 · report
MIACIFAR10 jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · 565b5f4760c965c4 · report
MIACIFAR100 jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · a37837f442664e59 · report
MIACelebA jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · e178434e00efeaa1 · report
MIAImageFolder jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · c1bd6f416b361a68 · report
MIASTL10 jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · c8669ab03b6eb470 · report
MIASVHN jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · 8ea9b61c668976e2 · report
execute_attack jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · c5d32ff1786210fb · report
load_member_data jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · 1e2284fb660b2cbc · report
nns_attack jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · af4ecede18d692d8 · report
print_result jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · ecf81b7416f17f20 · report
secmi_attack jinhaoduan/secmi/mia_evals/secmia.py official repository unverified MIT (permissive) · d67ce440a0baf665 · report
get_reverse_denoise_results jinhaoduan/SecMI-LDM/src/mia/secmi.py community (archive-listed) unverified Apache-2.0 (permissive) · 4f56353a85d6692e · report

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections