Papers › Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution

11 Jun 2021ACL 2021 5arXiv:2106.06361archive 2025-07-28

Fanchao Qi, Yuan YAO, Sophia Xu, Zhiyuan Liu, Maosong Sun

Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated, presenting serious security threats to real-world applications. Since existing textual backdoor attacks pay little attention to the invisibility of backdoors, they can be easily detected and blocked. In this work, we present invisible backdoors that are activated by a learnable combination of word substitution. We show that NLP models can be injected with backdoors that lead to a nearly 100% attack success rate, whereas being highly invisible to existing defense strategies and even human inspections. The results raise a serious alarm to the security of NLP models, which requires further research to be resolved. All the data and code of this paper are released at https://github.com/thunlp/BkdAtk-LWS.

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="2106.06361")

Code

Syntology Ran 1 of 11 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 11 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thunlp/BkdAtk-LWS officialmentioned in papermentioned on GitHubpytorchMIT 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

11 samples harvested; 1 ran; 0 honoured the contract we drafted; 10 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.

1ran · our draft was wrong
10unverified

Licence: 0 of the 11 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 thunlp/BkdAtk-LWS. “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.

sample_gumbel thunlp/BkdAtk-LWS/src/models/self_learning_poison_nn.py official repository ran · our draft was wrong MIT (permissive) · 7c913c414af7196f · report
evaluate thunlp/BkdAtk-LWS/src/models/bert_biclassifier.py official repository unverified MIT (permissive) · d4efdada25be8589 · report
generate_poisoned_data_with_static_pattern thunlp/BkdAtk-LWS/src/utils/static_data_poisoning.py official repository unverified MIT (permissive) · 74c83b2a628cb3e2 · report
generate_poisoned_dataset_with_static_pattern thunlp/BkdAtk-LWS/src/utils/static_data_poisoning.py official repository unverified MIT (permissive) · aee8bffefd2ce5c9 · report
get_accuracy_from_logits thunlp/BkdAtk-LWS/src/models/bert_biclassifier.py official repository unverified MIT (permissive) · 020b64bfa34d650d · report
gumbel_softmax thunlp/BkdAtk-LWS/src/models/self_learning_poison_nn.py official repository unverified MIT (permissive) · 14a7ead8fd4df5d1 · report
gumbel_softmax_sample thunlp/BkdAtk-LWS/src/models/self_learning_poison_nn.py official repository unverified MIT (permissive) · d32fc9578a779a8b · report
make_bert_biclassifier thunlp/BkdAtk-LWS/src/models/bert_biclassifier.py official repository unverified MIT (permissive) · 1f683bc79ea76e4f · report
prepare_dataset_for_bert thunlp/BkdAtk-LWS/src/utils/preprocessing.py official repository unverified MIT (permissive) · f72eb12e19b74436 · report
prepare_imdb_dataset thunlp/BkdAtk-LWS/src/experiments/domain_shift_imdb_eval.py official repository unverified MIT (permissive) · 56727e6229c24715 · report
prepare_imdb_dataset thunlp/BkdAtk-LWS/src/experiments/eval_onion_defense.py official repository unverified MIT (permissive) · d32ff2a5796b53b9 · report

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