Papers › Sound and Complete Neural Network Repair with Minimality and Locality Guarantees

Sound and Complete Neural Network Repair with Minimality and Locality Guarantees

14 Oct 2021ICLR 2022 4arXiv:2110.07682archive 2025-07-28

Feisi Fu, Wenchao Li

We present a novel methodology for repairing neural networks that use ReLU activation functions. Unlike existing methods that rely on modifying the weights of a neural network which can induce a global change in the function space, our approach applies only a localized change in the function space while still guaranteeing the removal of the buggy behavior. By leveraging the piecewise linear nature of ReLU networks, our approach can efficiently construct a patch network tailored to the linear region where the buggy input resides, which when combined with the original network, provably corrects the behavior on the buggy input. Our method is both sound and complete -- the repaired network is guaranteed to fix the buggy input, and a patch is guaranteed to be found for any buggy input. Moreover, our approach preserves the continuous piecewise linear nature of ReLU networks, automatically generalizes the repair to all the points including other undetected buggy inputs inside the repair region, is minimal in terms of changes in the function space, and guarantees that outputs on inputs away from the repair region are unaltered. On several benchmarks, we show that our approach significantly outperforms existing methods in terms of locality and limiting negative side effects. Our code is available on GitHub: https://github.com/BU-DEPEND-Lab/REASSURE.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2110.07682")

Code

Syntology Ran 8 of 13 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

bu-depend-lab/reassure officialmentioned in papermentioned on GitHubpytorchMIT report
k1majd/nnreplayer mentioned on GitHubtfMIT 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

13 samples harvested; 8 ran; 0 honoured the contract we drafted; 5 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

8ran
5unverified

Licence: 0 of the 13 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 bu-depend-lab/reassure. “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.

compare_models_on_dataloader bu-depend-lab/reassure/REASSURE/ExperimentTools.py official repository ran MIT (permissive) · 233a564117bdfcb5 · report
constraints_from_labels bu-depend-lab/reassure/REASSURE/ExperimentTools.py official repository ran MIT (permissive) · e314d6144e9ce6cc · report
construct_block_matrix bu-depend-lab/reassure/REASSURE/Tools.py official repository ran MIT (permissive) · b142724749abe662 · report
find_buggy_inputs bu-depend-lab/reassure/REASSURE/ExperimentTools.py official repository ran MIT (permissive) · ff48389def1d5526 · report
find_buggy_inputs bu-depend-lab/reassure/ICLR/Experiments/exp_tools.py official repository ran MIT (permissive) · 514c573f51772719 · report
get_linear_region bu-depend-lab/reassure/REASSURE/Tools.py official repository ran MIT (permissive) · 80b200c9b1dfb9f9 · report
specification_matrix_from_labels bu-depend-lab/reassure/ICLR/Experiments/exp_tools.py official repository ran MIT (permissive) · 6887baf1eea3e47c · report
test_diff_on_dataloader bu-depend-lab/reassure/ICLR/Experiments/exp_tools.py official repository ran MIT (permissive) · 83b115222955c019 · report
find_cex bu-depend-lab/reassure/ICLR/Experiments/HCAS/find_cex.py official repository unverified MIT (permissive) · 0f6eb1ab12223eed · report
imagenet_test_diff bu-depend-lab/reassure/ICLR/Experiments/ImageNet/ImageNetTools.py official repository unverified MIT (permissive) · f2f6bd7d1e943264 · report
linearize_model bu-depend-lab/reassure/REASSURE/Tools.py official repository unverified MIT (permissive) · a42894d62574bfe8 · report
load_test_data bu-depend-lab/reassure/ICLR/Experiments/ImageNet/ImageNetTools.py official repository unverified MIT (permissive) · 0414b3043c518f80 · report
read_imagenet_by_index bu-depend-lab/reassure/ICLR/Experiments/ImageNet/ImageNetTools.py official repository unverified MIT (permissive) · 9406edb1e6e2ebbf · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Repair

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