Papers › Practical Black-Box Attacks against Machine Learning

Practical Black-Box Attacks against Machine Learning

8 Feb 2016arXiv:1602.02697archive 2025-07-28

Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z. Berkay Celik, Ananthram Swami

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include having malicious content like malware identified as legitimate or controlling vehicle behavior. Yet, all existing adversarial example attacks require knowledge of either the model internals or its training data. We introduce the first practical demonstration of an attacker controlling a remotely hosted DNN with no such knowledge. Indeed, the only capability of our black-box adversary is to observe labels given by the DNN to chosen inputs. Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN. We use the local substitute to craft adversarial examples, and find that they are misclassified by the targeted DNN. To perform a real-world and properly-blinded evaluation, we attack a DNN hosted by MetaMind, an online deep learning API. We find that their DNN misclassifies 84.24% of the adversarial examples crafted with our substitute. We demonstrate the general applicability of our strategy to many ML techniques by conducting the same attack against models hosted by Amazon and Google, using logistic regression substitutes. They yield adversarial examples misclassified by Amazon and Google at rates of 96.19% and 88.94%. We also find that this black-box attack strategy is capable of evading defense strategies previously found to make adversarial example crafting harder.

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 11 code samples harvested from 3 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 3 repositories, 6 ran (5 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.

No sample is linked to this paper from 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

18 repositories listed; official and paper-mentioned ones first.

AngusG/cleverhans-attacking-bnns mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attacking Binarized Neural Networks (arXiv:1711.00449; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
HowToMakeABomb101/Hot2MakeAB0mbSite mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Technical Report on the CleverHans v2.1.0 Adversarial Examples Library (arXiv:1610.00768; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
adrian-botta/understanding_adversarial_examples mentioned on GitHubMITSyntology: not harvested report
cleverhans-lab/cleverhans mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping (arXiv:2402.03951; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
daisy611/fusion mentioned on GitHubSyntology: not harvested report
elites2k19/prism-attack mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
formal-verification-research/NJSMA mentioned on GitHubtfMITSyntology: not harvested report
iirishikaii/cleverhans mentioned on GitHubtfMITSyntology: not harvested report
inhopark94/ihpark mentioned on GitHubpytorchSyntology: not harvested report
jbinas/fortified-networks mentioned on GitHubtfMITSyntology: 7 samples, 2 ran (0 instrument-failed) · 5 unverified report
johnsonkee/graduate_design mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Technical Report on the CleverHans v2.1.0 Adversarial Examples Library (arXiv:1610.00768; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
openai/cleverhans mentioned on GitHubtfSyntology: not harvested report
probabilistic-jsma/probabilistic-jsma mentioned on GitHubtfSyntology: not harvested report
probabilistic-jsmas/probabilistic-jsmas mentioned on GitHubtfSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
shijiel2/cleverhans mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Explaining and Harnessing Adversarial Examples (arXiv:1412.6572; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 1 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
tensorflow/cleverhans mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Calibration through the Relationship with Adversarial Robustness (arXiv:2006.16375; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
yaq007/cleverhans mentioned on GitHubtfMITSyntology: not harvested report
MindCode-4/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Entropy Law: The Story Behind Data Compression and LLM Performance (arXiv:2407.06645; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 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.

3ran · honoured contract
1ran · our draft was wrong
2ran
5unverified

Licence: 4 of the 11 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

elites2k19/prism-attack community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
arg_type cleverhans/attacks/attack.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 50b95028f0c76d76 · report fixture: signature arg_names:tuple/1/str, kwargs:dict/0/? · returned tuple · level recorded 2026-09-22
jbinas/fortified-networks community (archive-listed) 7 samples, 2 ran (0 instrument-failed) · 5 unverified
dim2int fortnet_dae/resnet_tf.py ran MIT (permissive) · 2250a446cd9d9750 · report fixture: signature dim:Dimension/0/? · returned int · level recorded 2026-09-26
weight_rec_err run_blackbox.py ran MIT (permissive) · 3bb1443aebde61bb · report fixture: signature err:Tensor/0/float, wgt:Tensor/0/float · returned Tensor · level recorded 2026-09-26
compute_rec_err fortnet_dae/utils_tf.py unverified MIT (permissive) · 9b208439f9e823d7 · report
load_mnist in 35 papers datasets/utils_fashion_mnist.py unverified MIT (permissive) · 7802d4d8bfea87e4 · report
make_resnet_model fortnet_dae/models_tf.py unverified MIT (permissive) · 8f0d60173f7c6db6 · report
model_loss fortnet_dae/utils_tf.py unverified MIT (permissive) · befd82aa2271735d · report
probabilistic-jsmas/probabilistic-jsmas community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
norm_l0 start_stats.py ran · honoured contract fingerprinted no licence file found · pointer only · b265d88671923e2c · report fixture: signature a:ndarray/1/float, b:ndarray/1/float · returned int64 · level recorded 2026-09-22
norm_l1 start_stats.py ran · honoured contract fingerprinted no licence file found · pointer only · 3488e2e71e94a1a4 · report fixture: signature a:ndarray/2/float, b:ndarray/2/float · returned float64 · level recorded 2026-09-22
norm_l2 start_stats.py ran · honoured contract fingerprinted no licence file found · pointer only · 824708a335504c38 · report fixture: signature a:ndarray/1/float, b:ndarray/1/float · returned float64 · level recorded 2026-09-22

Tasks

BIG-bench Machine Learning

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