Papers › Towards Stable Backdoor Purification through Feature Shift Tuning
Towards Stable Backdoor Purification through Feature Shift Tuning
Rui Min, Zeyu Qin, Li Shen, Minhao Cheng
It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a small set of training samples. Although a line of defense methods is proposed to mitigate this threat, they either require complicated modifications to the training process or heavily rely on the specific model architecture, which makes them hard to deploy into real-world applications. Therefore, in this paper, we instead start with fine-tuning, one of the most common and easy-to-deploy backdoor defenses, through comprehensive evaluations against diverse attack scenarios. Observations made through initial experiments show that in contrast to the promising defensive results on high poisoning rates, vanilla tuning methods completely fail at low poisoning rate scenarios. Our analysis shows that with the low poisoning rate, the entanglement between backdoor and clean features undermines the effect of tuning-based defenses. Therefore, it is necessary to disentangle the backdoor and clean features in order to improve backdoor purification. To address this, we introduce Feature Shift Tuning (FST), a method for tuning-based backdoor purification. Specifically, FST encourages feature shifts by actively deviating the classifier weights from the originally compromised weights. Extensive experiments demonstrate that our FST provides consistently stable performance under different attack settings. Without complex parameter adjustments, FST also achieves much lower tuning costs, only 10 epochs. Our codes are available at https://github.com/AISafety-HKUST/stable_backdoor_purification.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Syntology holds a reference implementation of Feature Shift Tuning (FST), generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Feature Shift Tuning (FST)') (how to connect); the free check have('2310.01875') needs no token.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2310.01875")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2310.01875", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2310.01875")
Code
Syntology 13 code samples: 11 from 2 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 13: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 10 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); community: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); 2 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.
No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:
- aisafety-hkust/backdoor_safety_tuning, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 10 samples that ran have no recorded date.
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.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 4 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 13 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 2 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.
efd3b8b851a0f5e7 · report
fixture: signature parser:SimpleArgumentParser/0/? · returned SimpleArgumentParser · level recorded, date not recorded 5cfe5054c2c74fce · report
fixture: signature parser:SimpleParser/0/? · returned SimpleParser · level recorded 2026-09-24 1e9b4bedd9340fe0 · report
fixture: signature pratio:float/0/float, bs:int/0/int · returned int · level recorded 2026-09-24 ee9472dc60824bd5 · report
fixture: signature targets:ndarray/1/int, tlabel:int/0/int, pratio:float/0/float, p_num:NoneType/0/?, clean_label:bool/0/bool, train:bool/0/bool · returned ndarray · level recorded 2026-09-24 ad7ac1c21671d465 · report
fixture: signature targets:ndarray/1/int, tlabel:int/0/int, pratio:float/0/float, p_num:NoneType/0/?, clean_label:bool/0/bool, train:bool/0/bool · returned ndarray · level recorded 2026-09-24 ea3c60ddf40d46bc · report
fixture: signature path:str/0/str · returned bool · level recorded 2026-09-24 5840d4aeba85a839 · report
fixture: signature testloader:list/1/tuple, testmodel:callable/0/?, box:Box/0/?, poisoned:bool/0/bool, poitarget:bool/0/bool, midmodel:NoneType/0/?, passlabel:NoneType/0/?, feat_mask:NoneType/0/?, name:str/0/str · returned float · level recorded 2026-09-22 83953e32e89f7c00 · report
3c55a855cc155090 · report
ca2a104dfcdcd492 · report
0044d4606bb15d8c · report
fixture: returned tuple · level recorded, date not recorded 2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
f634daea78f08e78 · report
fixture: signature model:callable/0/?, criterion:callable/0/?, data_loader:DataLoaderWrapper/1/tuple · returned tuple · level recorded, date not recorded 1042d89ceda24cdb · report
fixture: signature model:callable/0/?, criterion:callable/0/?, optimizer:SGD/0/?, data_loader:SimpleDataLoader/1/tuple · returned tuple · level recorded, date not recorded Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.
2 assemblies on this paper: 1 harvested, 1 generated.
generated Assembly for Feature Shift Tuning (FST) (graph method: Feature Shift Tuning (FST)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).
label matches by construction: the code was generated for this method (not judged by a model)
- compute_w_gradient_with_deviation entry · level 3 · ran · violated contract ·
217db7ac1c8b0e55ef4b8c014895d6064eaafd7869d7237f2e2418edaafbd4c9
harvested Assembly for Feature Shift Tuning (FST) (graph method: Feature Shift Tuning (FST)). 2 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
- purify entry · level 0 · unverified ·
ca2a104dfcdcd492 - test helper · level 1 · ran · honoured contract ·
5840d4aeba85a839
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2310.01875") returns these assemblies with each brick's role and wiring (how to connect).
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