Papers › Attacking Binarized Neural Networks

Attacking Binarized Neural Networks

1 Nov 2017ICLR 2018 1arXiv:1711.00449archive 2025-07-28

Angus Galloway, Graham W. Taylor, Medhat Moussa

Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster forward pass when implemented with efficient bitwise operations. We propose a third benefit of very low-precision neural networks: improved robustness against some adversarial attacks, and in the worst case, performance that is on par with full-precision models. We focus on the very low-precision case where weights and activations are both quantized to ±1, and note that stochastically quantizing weights in just one layer can sharply reduce the impact of iterative attacks. We observe that non-scaled binary neural networks exhibit a similar effect to the original defensive distillation procedure that led to gradient masking, and a false notion of security. We address this by conducting both black-box and white-box experiments with binary models that do not artificially mask gradients.

PaperPDFConference PDFCodeCode 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 19 code samples harvested from 1 repository linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 5 ran (5 with no instrument failure; 0 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

AngusG/cleverhans-attacking-bnns officialmentioned in papertfMITSyntology: 19 samples, 5 ran (0 instrument-failed) · 14 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

19 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
4ran
14unverified

Licence: 19 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, 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 AngusG/cleverhans-attacking-bnns. “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.

AngusG/cleverhans-attacking-bnns official repository 19 samples, 5 ran (0 instrument-failed) · 14 unverified
batch_indices in 5 papers cleverhans/utils.py ran MIT recorded; this copy not marked cleared · pointer only · 96b581b6ac010981 · report fixture: signature batch_nb:int/0/int, data_length:int/0/int, batch_size:int/0/int · returned tuple · level recorded 2026-09-24
hard_sigmoid in 15 papers cleverhans_tutorials/tutorial_models.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 33ce7291d7174c33 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
model_loss cleverhans/utils_tf.py ran MIT recorded; this copy not marked cleared · pointer only · 24e8cacf2e978687 · report fixture: signature y:EagerTensor/2/float, model:MockModel/0/?, mean:bool/0/bool · returned EagerTensor · level recorded 2026-09-25
other_classes in 5 papers cleverhans/utils.py ran · honoured contract fingerprinted MIT recorded; this copy not marked cleared · pointer only · 563a92a1c7232061 · report fixture: signature nb_classes:int/0/int, class_ind:int/0/int · returned list · level recorded 2026-09-24
to_categorical in 25 papers
census: 3 implementations from 5 papers, 1 distinct output on one shared input
cleverhans/utils.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 436b1ff1875d0cc7 · report fixture: signature y:list/1/int, num_classes:int/0/int · returned ndarray · level recorded 2026-09-25
batch_norm_relu in 5 papers cleverhans_tutorials/resnet_model.py unverified MIT (permissive) here; the stored copy is pointer only · 9a841e39a73659c0 · report
cnn_model cleverhans/utils_keras.py unverified MIT recorded; this copy not marked cleared · pointer only · 69dbec087f603dc2 · report
conv_2d in 7 papers cleverhans/utils_keras.py unverified MIT recorded; this copy not marked cleared · pointer only · 4e8d1df070cb5f83 · report
data_mnist cleverhans/utils_mnist.py unverified MIT recorded; this copy not marked cleared · pointer only · 5f6a796fa47c9ff8 · report
fgm in 5 papers cleverhans/attacks_tf.py unverified MIT recorded; this copy not marked cleared · pointer only · 46c4fbb3b28111b4 · report
fgsm in 14 papers cleverhans/attacks.py unverified MIT recorded; this copy not marked cleared · pointer only · 669a4a70d107c4a4 · report
fgsm in 14 papers cleverhans/attacks_tf.py unverified MIT recorded; this copy not marked cleared · pointer only · ab300465511282c2 · report
jsma cleverhans/attacks.py unverified MIT recorded; this copy not marked cleared · pointer only · 48e3be63336a0ac5 · report
normalized_sign_changes_op cleverhans/utils_tf.py unverified MIT recorded; this copy not marked cleared · pointer only · 457d5efa3991f205 · report
quantize in 70 papers
census: 8 implementations from 11 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
cleverhans_tutorials/resnet_model.py unverified MIT recorded; this copy not marked cleared · pointer only · fb9a05da9fb0eb6e · report
quantize_grad cleverhans_tutorials/resnet_model.py unverified MIT recorded; this copy not marked cleared · pointer only · 88e4e6b729fd7669 · report
sign_changes_count_op cleverhans/utils_tf.py unverified MIT recorded; this copy not marked cleared · pointer only · 45a3aac96deaa69d · report
vatm cleverhans/attacks.py unverified MIT recorded; this copy not marked cleared · pointer only · 265a717d9cb4752d · report
vatm cleverhans/attacks_tf.py unverified MIT recorded; this copy not marked cleared · pointer only · 1d76eb5891f63a2f · report

Tasks

Quantization

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