Papers › SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer

29 Feb 2024arXiv:2402.18945archive 2025-07-28

Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu

Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper, we introduce maxEntropy, an entropy-based poisoning filter that mitigates such risks. To overcome the limitations of manual target setting and explicit triggers, we propose SynGhost, an invisible and universal task-agnostic backdoor attack via syntactic transfer, further exposing vulnerabilities in pre-trained language models (PLMs). Specifically, SynGhost injects multiple syntactic backdoors into the pre-training space through corpus poisoning, while preserving the PLM's pre-training capabilities. Second, SynGhost adaptively selects optimal targets based on contrastive learning, creating a uniform distribution in the pre-training space. To identify syntactic differences, we also introduce an awareness module to minimize interference between backdoors. Experiments show that SynGhost poses significant threats and can transfer to various downstream tasks. Furthermore, SynGhost resists defenses based on perplexity, fine-pruning, and maxEntropy. The code is available at https://github.com/Zhou-CyberSecurity-AI/SynGhost.

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="2402.18945")

Code

Syntology Ran 4 of 10 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhou-cybersecurity-ai/synghost officialmentioned in paperpytorch 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

10 samples harvested; 4 ran; 0 honoured the contract we drafted; 6 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.

4ran
6unverified

Licence: 10 of the 10 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 zhou-cybersecurity-ai/synghost. “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.

collate_fn zhou-cybersecurity-ai/synghost/code/synGhostToPLM.py official repository ran no licence file found · pointer only · bcac51a4aea23706 · report
comp_loss zhou-cybersecurity-ai/synghost/code/synGhost_FineTuning.py official repository ran no licence file found · pointer only · 41a6c03c61b9e31a · report
constuct_target zhou-cybersecurity-ai/synghost/dataset_utils/Plain_analysis_dataset.py official repository ran no licence file found · pointer only · 43faeb3d12188522 · report
getsampledataset zhou-cybersecurity-ai/synghost/synGhost_Generation/generate_by_openattack_imdb.py official repository ran no licence file found · pointer only · 79103aee91fea6de · report
comp_loss zhou-cybersecurity-ai/synghost/code/synGhost_peft.py official repository unverified no licence file found · pointer only · 5d5c7151647810d4 · report
compute_hidden zhou-cybersecurity-ai/synghost/code/synGhost_FineTuning.py official repository unverified no licence file found · pointer only · f61171675ffca866 · report
compute_hidden zhou-cybersecurity-ai/synghost/code/synGhost_peft.py official repository unverified no licence file found · pointer only · 5719e5edf8bf1c3f · report
construct_sentence zhou-cybersecurity-ai/synghost/dataset_utils/Plain_analysis_dataset.py official repository unverified no licence file found · pointer only · 136f9eaa2ebe7769 · report
generate_poison zhou-cybersecurity-ai/synghost/synGhost_Generation/generate_by_openattack_imdb.py official repository unverified no licence file found · pointer only · 7327b24c9b60d0f1 · report
generate_poison zhou-cybersecurity-ai/synghost/synGhost_Generation/generate_by_openattack_wikitext.py official repository unverified no licence file found · pointer only · 5c4d2ffef07ddaff · report

Tasks

Backdoor AttackContrastive LearningNatural Language Understanding

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

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