Papers › On the Privacy Effect of Data Enhancement via the Lens of Memorization

On the Privacy Effect of Data Enhancement via the Lens of Memorization

17 Aug 2022arXiv:2208.08270archive 2025-07-28

Xiao Li, Qiongxiu Li, Zhanhao Hu, Xiaolin Hu

Machine learning poses severe privacy concerns as it has been shown that the learned models can reveal sensitive information about their training data. Many works have investigated the effect of widely adopted data augmentation and adversarial training techniques, termed data enhancement in the paper, on the privacy leakage of machine learning models. Such privacy effects are often measured by membership inference attacks (MIAs), which aim to identify whether a particular example belongs to the training set or not. We propose to investigate privacy from a new perspective called memorization. Through the lens of memorization, we find that previously deployed MIAs produce misleading results as they are less likely to identify samples with higher privacy risks as members compared to samples with low privacy risks. To solve this problem, we deploy a recent attack that can capture individual samples' memorization degrees for evaluation. Through extensive experiments, we unveil several findings about the connections between three essential properties of machine learning models, including privacy, generalization gap, and adversarial robustness. We demonstrate that the generalization gap and privacy leakage are less correlated than those of the previous results. Moreover, there is not necessarily a trade-off between adversarial robustness and privacy as stronger adversarial robustness does not make the model more susceptible to privacy attacks.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 14 ran (13 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lixiaothu/privacy_and_aug officialmentioned in paperpytorchMITSyntology: 17 samples, 14 ran (1 instrument-failed) · 3 unverified 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

17 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
13ran
3unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lixiaothu/privacy_and_aug. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

lixiaothu/privacy_and_aug official repository 17 samples, 14 ran (1 instrument-failed) · 3 unverified
ROC_curve eval_privacy.py ran MIT (permissive) · 2fef971a40606cc9 · report fixture: signature y:ndarray/1/int, pred:ndarray/1/float, save:bool/0/bool, show:bool/0/bool, name:str/0/str · returned tuple · level recorded 2026-09-25
ResNet18 in 174 papers models/ResNet.py ran MIT (permissive) · e646ab652ba06157 · report fixture: signature in_dim:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
ResNet34 in 91 papers models/ResNet.py ran MIT (permissive) · bdfee6e9a24e258f · report fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
ResNet9 models/ResNet.py ran MIT (permissive) · 0ed6b1f3db7c187f · report fixture: signature in_dim:int/0/int, num_classes:int/0/int · returned ResNet · level recorded 2026-09-25
SoftLabelNLL inference.py ran fingerprinted MIT (permissive) · 28d5109e1b7c352f · report fixture: signature predicted:Tensor/2/float, target:Tensor/2/float, reduce:bool/0/bool · returned Tensor · level recorded 2026-09-25
cal_adv advtrain.py ran MIT (permissive) · dae43d0752d48a19 · report fixture: signature model:callable/0/?, criterion:callable/0/?, aug_type:str/0/str, imgs:Tensor/2/float, cids:Tensor/1/int, eps:int/0/int · returned Tensor · level recorded 2026-09-25
computeMetrics utils_h.py ran MIT (permissive) · 91e35de2120c235c · report fixture: signature scores:tuple/1/ndarray, FPR:float/0/float · returned dict · level recorded 2026-09-25
create_path utils.py ran fingerprinted MIT (permissive) · cbc1ea670dc40bb6 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-25
diff_in_weights in 9 papers trades_awp.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 4170809219439d13 · report fixture: signature model:callable/0/?, proxy:callable/0/? · returned OrderedDict · level recorded 2026-09-22
fake_inputs utils_h.py ran MIT (permissive) · 7fc21d4ca47b24eb · report fixture: signature inputs:Tensor/4/float, disc_net:callable/0/?, eps:float/0/float, eps_range:float/0/float, clip_min:float/0/float, clip_max:float/0/float · returned tuple · level recorded 2026-09-25
load_model in 479 papers utils.py ran MIT (permissive) · 0619c0c4d30c7511 · report fixture: signature model_path:str/0/str, model:callable/0/?, device:str/0/str · returned dict · level recorded 2026-09-25
log_display utils.py ran MIT (permissive) · 55fbccf29c619901 · report fixture: signature epoch:int/0/int, global_step:int/0/int, time_elapse:float/0/float, loss:float/0/float, accuracy:float/0/float, message:str/0/str · returned str · level recorded 2026-09-25
normal in 11 papers eval_privacy.py ran MIT (permissive) · 5f7d0e7a485b4a1a · report fixture: signature mu:ndarray/1/float, sigma2:ndarray/1/float, x:ndarray/1/float, multi:bool/0/bool · returned float64 · level recorded 2026-09-25
test in 377 papers utils_h.py ran MIT (permissive) · 79317dc18351550d · report fixture: signature net:callable/0/?, loader:list/1/tuple, device:str/0/str, attacker:callable/0/?, adv_args:dict/0/?, defender:NoneType/0/?, defender_info:NoneType/0/?, display:bool/0/bool, target_net:callable/0/? · returned tuple · level recorded 2026-09-25
get_cifar100_datasets dataset.py unverified MIT (permissive) · afa8aab43a77d953 · report
get_cifar10_datasets dataset.py unverified MIT (permissive) · 2410b3bdf17c6a79 · report
get_loaders in 51 papers dataset.py unverified MIT (permissive) · e259e3b8e5627125 · report

Tasks

Adversarial RobustnessData AugmentationMemorization

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