Papers › Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense

Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense

1 Oct 2023arXiv:2310.00542archive 2025-07-28

Hua Ma, Shang Wang, Yansong Gao, Zhi Zhang, Huming Qiu, Minhui Xue, Alsharif Abuadbba, Anmin Fu, Surya Nepal, Derek Abbott

All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class activates the implanted backdoor when the secret trigger is present. Existing defense strategies overwhelmingly focus on countering VCB attacks, especially those that are source-class-agnostic. This narrow focus neglects the potential threat of other simpler yet general backdoor types, leading to false security implications. This study introduces a new, simple, and general type of backdoor attack coined as the horizontal class backdoor (HCB) that trivially breaches the class dependence characteristic of the VCB, bringing a fresh perspective to the community. HCB is now activated when the trigger is presented together with an innocuous feature, regardless of class. For example, the facial recognition model misclassifies a person who wears sunglasses with a smiling innocuous feature into the targeted person, such as an administrator, regardless of which person. The key is that these innocuous features are horizontally shared among classes but are only exhibited by partial samples per class. Extensive experiments on attacking performance across various tasks, including MNIST, facial recognition, traffic sign recognition, object detection, and medical diagnosis, confirm the high efficiency and effectiveness of the HCB. We rigorously evaluated the evasiveness of the HCB against a series of eleven representative countermeasures, including Fine-Pruning (RAID 18'), STRIP (ACSAC 19'), Neural Cleanse (Oakland 19'), ABS (CCS 19'), Februus (ACSAC 20'), NAD (ICLR 21'), MNTD (Oakland 21'), SCAn (USENIX SEC 21'), MOTH (Oakland 22'), Beatrix (NDSS 23'), and MM-BD (Oakland 24'). None of these countermeasures prove robustness, even when employing a simplistic trigger, such as a small and static white-square patch.

PaperPDFCodeCode 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="2310.00542")

Code

Syntology Ran 15 of 22 code samples harvested from 5 repositories linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 3 ran · fixture could not drive it; 9 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran; found in paper text by Syntology: 17 samples from 4 repositories, 10 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shihe98/hcb officialmentioned in paperpytorchMIT 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

22 samples harvested; 15 ran; 0 honoured the contract we drafted; 7 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.

3ran · our draft was wrong
3ran · fixture could not drive it
9ran
7unverified

Licence: 7 of the 22 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 5 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

getTrans shihe98/HCB/GTSRB/Model/utils_model_outsourcing.py official repository ran MIT (permissive) · 2267cf1bf4bcc344 · report
get_backdoor_train shihe98/hcb/GTSRB/Model/utils_model_outsourcing.py official repository ran MIT (permissive) · 92f6ebd6ff7231bf · report
get_triggerData shihe98/hcb/GTSRB/Model/utils_model_outsourcing.py official repository ran · fixture could not drive it MIT (permissive) · 8d23eca23f539e84 · report
test_accuracy shihe98/HCB/GTSRB/Model/utils_model_outsourcing.py official repository ran MIT (permissive) · 39f23426bccb25cd · report
build_base_model TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py found in paper text by Syntology ran MIT (permissive) · 874d05e9545938a1 · report
build_base_model TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py found in paper text by Syntology ran MIT (permissive) · e15bd05849cc4332 · report
build_model TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py found in paper text by Syntology ran MIT (permissive) · 45579f864dad8357 · report
channel_shuffle naiyeleo/ABS/TrojAI_competition/round2/abs_pytorch1_color_simple_filter4_8_6_3_determinism.py found in paper text by Syntology ran · our draft was wrong fingerprinted no licence file found · pointer only · b9da06d4f527dd6c · report
deprocess naiyeleo/ABS/TrojAI_competition/round1/abs_pytorch_round1.py found in paper text by Syntology ran · fixture could not drive it fingerprinted no licence file found · pointer only · f7334fdb122d1c51 · report
no AdelaideAuto-IDLab/Februus/face/Februus.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 7d8578b316548dd5 · report
options_to_json TDteach/Demon-in-the-Variant/pysrc/utils.py found in paper text by Syntology ran MIT (permissive) · 5117993745c7bae0 · report
pca TDteach/Demon-in-the-Variant/tsne.py found in paper text by Syntology ran fingerprinted MIT (permissive) · f60cb3cead55f81b · report
preprocess naiyeleo/ABS/TrojAI_competition/round1/abs_pytorch_round1.py found in paper text by Syntology ran · fixture could not drive it fingerprinted no licence file found · pointer only · 06fcb055d047c43d · report
x2p TDteach/Demon-in-the-Variant/tsne.py found in paper text by Syntology ran fingerprinted MIT (permissive) · 654e67f1bec03fc8 · report
Hbeta TDteach/Demon-in-the-Variant/tsne.py found in paper text by Syntology unverified MIT (permissive) · 77fb404ad78a22d9 · report
Trigger Gwinhen/MOTH/src/inversion.py found in paper text by Syntology unverified MIT (permissive) · 098112848b087db6 · report
getlayer_output naiyeleo/ABS/abs.py found in paper text by Syntology unverified no licence file found · pointer only · dd61aa4cb050a0de · report
parse_record TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py found in paper text by Syntology unverified MIT (permissive) · 4e8aeb9bb95b5b61 · report
poison_one AdelaideAuto-IDLab/Februus/face/Februus.py found in paper text by Syntology unverified no licence file found · pointer only · 50d5614af6b6f7c5 · report
split_model TDteach/Demon-in-the-Variant/pysrc/train_cifar10.py found in paper text by Syntology unverified MIT (permissive) · a756332b6091f3b8 · report
split_model TDteach/Demon-in-the-Variant/pysrc/train_gtsrb.py found in paper text by Syntology unverified MIT (permissive) · 69b6b3cbe737eaf2 · report
unno identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 1ed9bb9126b74824 · report

Tasks

Backdoor AttackMedical DiagnosisObject DetectionTraffic Sign Recognitionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

1 archive method tag without a method page not shown.

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