Papers › One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training

12 Aug 2023ICCV 2023 1arXiv:2308.07934archive 2025-07-28

Jianshuo Dong, Han Qiu, Yiming Li, Tianwei Zhang, Yuanjie Li, Zeqi Lai, Chao Zhang, Shu-Tao Xia

Deep neural networks (DNNs) are widely deployed on real-world devices. Concerns regarding their security have gained great attention from researchers. Recently, a new weight modification attack called bit flip attack (BFA) was proposed, which exploits memory fault inject techniques such as row hammer to attack quantized models in the deployment stage. With only a few bit flips, the target model can be rendered useless as a random guesser or even be implanted with malicious functionalities. In this work, we seek to further reduce the number of bit flips. We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release. This high-risk model, obtained coupled with a corresponding malicious model, behaves normally and can escape various detection methods. The results on benchmark datasets show that an adversary can easily convert this high-risk but normal model to a malicious one on victim's side by \textbf{flipping only one critical bit} on average in the deployment stage. Moreover, our attack still poses a significant threat even when defenses are employed. The codes for reproducing main experiments are available at \url{https://github.com/jianshuod/TBA}.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2308.07934")

Code

Syntology Ran 5 of 19 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jianshuod/tba officialmentioned in paperpytorchApache-2.0 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; 0 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

5ran
14unverified

Licence: 0 of the 19 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 jianshuod/tba. “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.

resnet18 jianshuod/tba/models/resnet_imagenet.py official repository ran Apache-2.0 (permissive) · d4ce9659619b8ea1 · report
resnet20 jianshuod/tba/models/vanilla_resnet.py official repository ran Apache-2.0 (permissive) · 182a7f2d3cc58f1f · report
resnet20_mid jianshuod/tba/models/vanilla_resnet.py official repository ran Apache-2.0 (permissive) · ff957dd4b649ffa9 · report
resnet32 jianshuod/tba/models/vanilla_resnet.py official repository ran Apache-2.0 (permissive) · 4d1d3d6506466614 · report
resnet34 jianshuod/tba/models/resnet_imagenet.py official repository ran Apache-2.0 (permissive) · 310efac4b79ed4b8 · report
ResNet18_quan jianshuod/tba/models/quan_resnet_cifar.py official repository unverified Apache-2.0 (permissive) · ba94bd83c4dc0e85 · report
ResNet18_quan_mid jianshuod/tba/models/quan_resnet_cifar.py official repository unverified Apache-2.0 (permissive) · 5f98bf5121225ab2 · report
ResNet34_quan jianshuod/tba/models/quan_resnet_cifar.py official repository unverified Apache-2.0 (permissive) · d4579dc79a9b3ea5 · report
conv1x1 jianshuod/tba/models/quan_resnet_imagenet.py official repository unverified Apache-2.0 (permissive) · b64260518ba09713 · report
conv3x3 jianshuod/tba/models/quan_resnet_imagenet.py official repository unverified Apache-2.0 (permissive) · 7fccbfe95159927d · report
loss_func_b_hat jianshuod/TBA/opt/lf.py official repository unverified Apache-2.0 (permissive) · fe156b7419dee060 · report
make_layers jianshuod/tba/models/quan_vgg_imagenet.py official repository unverified Apache-2.0 (permissive) · afa7785be020b743 · report
resnet101 jianshuod/tba/models/quan_resnet_imagenet.py official repository unverified Apache-2.0 (permissive) · d12f282b670852c9 · report
resnet20_quan jianshuod/tba/models/quan_resnet.py official repository unverified Apache-2.0 (permissive) · f0237985c42087d8 · report
resnet20_quan_mid jianshuod/tba/models/quan_resnet.py official repository unverified Apache-2.0 (permissive) · a198772dc6aa53e5 · report
resnet32_quan jianshuod/tba/models/quan_resnet.py official repository unverified Apache-2.0 (permissive) · 3c7f8e948fc4bb96 · report
vgg16_quan jianshuod/tba/models/quan_vgg_cifar.py official repository unverified Apache-2.0 (permissive) · 15ecbad4de186a7e · report
vgg16_quan_mid jianshuod/tba/models/quan_vgg_cifar.py official repository unverified Apache-2.0 (permissive) · 2c763161356ce3ef · report
vgg19_quan jianshuod/tba/models/quan_vgg_cifar.py official repository unverified Apache-2.0 (permissive) · c1939f569307c9c1 · report

Tasks

All

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FLIP

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