Papers › Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks

28 Jan 2022arXiv:2201.12179archive 2025-07-28

Lukas Struppek, Dominik Hintersdorf, Antonio De Almeida Correia, Antonia Adler, Kristian Kersting

Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge. Previous research has developed generative MIAs that use generative adversarial networks (GANs) as image priors tailored to a specific target model. This makes the attacks time- and resource-consuming, inflexible, and susceptible to distributional shifts between datasets. To overcome these drawbacks, we present Plug & Play Attacks, which relax the dependency between the target model and image prior, and enable the use of a single GAN to attack a wide range of targets, requiring only minor adjustments to the attack. Moreover, we show that powerful MIAs are possible even with publicly available pre-trained GANs and under strong distributional shifts, for which previous approaches fail to produce meaningful results. Our extensive evaluation confirms the improved robustness and flexibility of Plug & Play Attacks and their ability to create high-quality images revealing sensitive class characteristics.

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="2201.12179")

Code

Syntology Ran 16 of 36 code samples harvested from 6 repositories linked to this paper; 20 have no recorded run. Of those that ran: 1 ran · violated contract; 8 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 3 ran; community (archive-listed): 1 sample from 1 repository, 1 ran; found in paper text by Syntology: 31 samples from 4 repositories, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

LukasStruppek/Plug-and-Play-Attacks officialmentioned in papermentioned on GitHubpytorch 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

36 samples harvested; 16 ran; 0 honoured the contract we drafted; 20 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.

1ran · violated contract
8ran · our draft was wrong
7ran
20unverified

Licence: 5 of the 36 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 6 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.

create_initial_vectors lukasstruppek/plug-and-play-attacks/attack.py official repository ran · our draft was wrong MIT (permissive) · fa4ee3a3e0b099a5 · report
poincare_loss LukasStruppek/Plug-and-Play-Attacks/attacks/optimize.py official repository ran · our draft was wrong MIT (permissive) · 9eeaa864194d2b12 · report
write_precision_list lukasstruppek/plug-and-play-attacks/attack.py official repository ran · our draft was wrong MIT (permissive) · 410e110382621c40 · report
Optimization LukasStruppek/Plug-and-Play-Attacks/attacks/optimize.py official repository unverified MIT (permissive) · c29018fcd5fb7cfa · report
create_image lukasstruppek/class_attribute_inference_attacks/attack_ppa.py community (archive-listed) ran · our draft was wrong MIT (permissive) · b4f439c13b63055d · report
ContextNetwork AI-secure/GMI-Attack/Celeba/generator.py found in paper text by Syntology ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 390270b249117165 · report
D_arch ajbrock/BigGAN-PyTorch/BigGAN.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · 85eb95cce203dfc7 · report
G_arch ajbrock/BigGAN-PyTorch/BigGAN.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · e8c308c9283407d7 · report
IdentityGenerator AI-secure/GMI-Attack/Celeba/generator.py found in paper text by Syntology ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 29f3f93ece1d2af8 · report
MineGAN wangkua1/vmi/attack_stylegan.py found in paper text by Syntology ran no licence file found · pointer only · 3a4c1d8b783d177b · report
dconv_bn_relu AI-secure/GMI-Attack/Celeba/generator.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 17b094c69aebe5ed · report
find_classes ajbrock/BigGAN-PyTorch/datasets.py found in paper text by Syntology ran MIT (permissive) · 52d10a10fb72fb9f · report
get_deprocessor SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology ran MIT (permissive) · d8f4bcdc2662ccd8 · report
gram_schmidt ajbrock/BigGAN-PyTorch/layers.py found in paper text by Syntology ran · our draft was wrong MIT (permissive) · c41836f3e51fa8f1 · report
is_image_file ajbrock/BigGAN-PyTorch/datasets.py found in paper text by Syntology ran MIT (permissive) · 4e6a8faaf8e44abe · report
l2normalize ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py found in paper text by Syntology ran · violated contract fingerprinted MIT (permissive) · 9b11458d7d1ec61c · report
make_dataset ajbrock/BigGAN-PyTorch/datasets.py found in paper text by Syntology ran MIT (permissive) · 79e61b6269a450e8 · report
D_arch ajbrock/BigGAN-PyTorch/BigGANdeep.py found in paper text by Syntology unverified MIT (permissive) · a99a05ac52533be9 · report
G_arch ajbrock/BigGAN-PyTorch/BigGANdeep.py found in paper text by Syntology unverified MIT (permissive) · 44d6a6343f6eb182 · report
InversionNet AI-secure/GMI-Attack/Celeba/generator.py found in paper text by Syntology unverified no licence file found · pointer only · 3b56f1895629495e · report
denorm ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py found in paper text by Syntology unverified MIT (permissive) · 6e16337c88174e00 · report
dist_inversion SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology unverified MIT (permissive) · ef6717b52bd16215 · report
log_sum_exp SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology unverified MIT (permissive) · 265774c3878176e5 · report
loss_dcgan_dis ajbrock/BigGAN-PyTorch/losses.py found in paper text by Syntology unverified MIT (permissive) · 982a26492dc6b7fb · report
loss_dcgan_gen ajbrock/BigGAN-PyTorch/losses.py found in paper text by Syntology unverified MIT (permissive) · 6c34831223553b6f · report
loss_hinge_dis ajbrock/BigGAN-PyTorch/losses.py found in paper text by Syntology unverified MIT (permissive) · 290cd37ab0098d5c · report
low2high SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology unverified MIT (permissive) · dece9a6e3aff80cf · report
numpy_calculate_frechet_distance ajbrock/BigGAN-PyTorch/inception_utils.py found in paper text by Syntology unverified MIT (permissive) · 54af0200eab3163f · report
power_iteration ajbrock/BigGAN-PyTorch/layers.py found in paper text by Syntology unverified MIT (permissive) · 28d3a35157f2916d · report
proj ajbrock/BigGAN-PyTorch/layers.py found in paper text by Syntology unverified MIT (permissive) · 4015ab1f3ab9b881 · report
reparameterize SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology unverified MIT (permissive) · 3c7bb63b7354af4f · report
run ajbrock/BigGAN-PyTorch/inception_tf13.py found in paper text by Syntology unverified MIT (permissive) · ac122c2c1495ce94 · report
save_tensor_images SCccc21/Knowledge-Enriched-DMI/attack.py found in paper text by Syntology unverified MIT (permissive) · ddce921e8795376f · report
sqrt_newton_schulz ajbrock/BigGAN-PyTorch/inception_utils.py found in paper text by Syntology unverified MIT (permissive) · c39eebccbb5e86a6 · report
torch_cov ajbrock/BigGAN-PyTorch/inception_utils.py found in paper text by Syntology unverified MIT (permissive) · 4a2b2f288be2a186 · report
truncated_z_sample ajbrock/BigGAN-PyTorch/TFHub/biggan_v1.py found in paper text by Syntology unverified MIT (permissive) · b72f0c209b7b64be · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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