Papers › TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

28 Jul 2018arXiv:1807.10875archive 2025-07-28

Augustus Odena, Ian Goodfellow

Machine learning models are notoriously difficult to interpret and debug. This is particularly true of neural networks. In this work, we introduce automated software testing techniques for neural networks that are well-suited to discovering errors which occur only for rare inputs. Specifically, we develop coverage-guided fuzzing (CGF) methods for neural networks. In CGF, random mutations of inputs to a neural network are guided by a coverage metric toward the goal of satisfying user-specified constraints. We describe how fast approximate nearest neighbor algorithms can provide this coverage metric. We then discuss the application of CGF to the following goals: finding numerical errors in trained neural networks, generating disagreements between neural networks and quantized versions of those networks, and surfacing undesirable behavior in character level language models. Finally, we release an open source library called TensorFuzz that implements the described techniques.

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 12 code samples harvested from 2 repositories linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 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): 12 samples from 2 repositories, 8 ran (7 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

DataScienceNigeria/Research-Review mentioned on GitHubSyntology: not harvested report
brain-research/tensorfuzz mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dlshriver/tensorfuzz mentioned on GitHubtfApache-2.0Syntology: 11 samples, 7 ran (0 instrument-failed) · 4 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

12 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 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
7ran
4unverified

Licence: 0 of the 12 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; the list below is grouped by repository, each group headed by its name and what it is to the 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.

brain-research/tensorfuzz community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
metadata_function examples/dcgan/dcgan_fuzzer.py ran · our draft was wrong Apache-2.0 (permissive) · 0a8e1fe36f7ef1b3 · report fixture: signature metadata_batches:tuple/1/Tensor · returned list · level recorded 2026-09-22
dlshriver/tensorfuzz community (archive-listed) 11 samples, 7 ran (0 instrument-failed) · 4 unverified
all_logit_coverage_function tensorfuzz/coverage_functions.py ran Apache-2.0 (permissive) · fff6bfa97956f1cb · report fixture: signature coverage_batches:list/1/ndarray · returned list · level recorded 2026-09-26
do_basic_mutations tensorfuzz/mutation_functions.py ran Apache-2.0 (permissive) · 662cd0653cfa5331 · report fixture: signature corpus_element:CorpusElement/0/?, mutations_count:int/0/int, constraint:float/0/float, a_min:float/0/float, a_max:float/0/float · returned list · level recorded 2026-09-26
raw_logit_coverage_function tensorfuzz/coverage_functions.py ran Apache-2.0 (permissive) · 0b7efaa224c7baae · report fixture: signature coverage_batches:list/1/ndarray · returned list · level recorded 2026-09-26
read32 tensorfuzz/dataset.py ran Apache-2.0 (permissive) · 614450805ad8930b · report fixture: signature bytestream:BytesIO/0/? · returned uint32 · level recorded 2026-09-26
recent_sample_function tensorfuzz/sample_functions.py ran Apache-2.0 (permissive) · 32a0c2d51e97db34 · report fixture: signature input_corpus:InputCorpus/0/? · returned CorpusElement · level recorded 2026-09-26
seed_corpus_from_numpy_arrays tensorfuzz/corpus.py ran Apache-2.0 (permissive) · 63f01cf6db93ebf5 · report fixture: signature numpy_arrays:list/1/list, coverage_function:callable/0/?, metadata_function:callable/0/?, fetch_function:callable/0/? · returned list · level recorded 2026-09-26
uniform_sample_function tensorfuzz/sample_functions.py ran Apache-2.0 (permissive) · f72e38544e9a194e · report fixture: signature input_corpus:InputCorpus/0/? · returned CorpusElement · level recorded 2026-09-26
build_feed_dict tensorfuzz/fuzz_utils.py unverified Apache-2.0 (permissive) · f0c844600ff3617f · report
dataset in 10 papers tensorfuzz/dataset.py unverified Apache-2.0 (permissive) · 164f1de8053b6538 · report
download in 53 papers tensorfuzz/dataset.py unverified Apache-2.0 (permissive) · 0d65e022d1e2371e · report
get_tensors_from_checkpoint tensorfuzz/fuzz_utils.py unverified Apache-2.0 (permissive) · 01e04256351ed81e · report

Tasks

software testing

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