SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.09786 · ICML · 2024

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency

Yiming Li, Wei Luo, Linshan Hou, Ruili Feng, Zhongyun Hua, Leo Zhang

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2405.09786.json · badge: /api/ran/2405.09786.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
thuyimingli/backdoorbox canonical (classifier label)
classifier basis: classifier_2025
2 ran · 4 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Base Ran
ran on a synthesized input · constructed an object; no result was computed
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("b54ad0b1951a013f")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Log Ran
ran on a synthesized input · constructed an object; no result was computed
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("e6ae719ff0fda7d5")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from thuyimingli/backdoorbox
pointer only; the stored copy get_code serves, from thuyimingli/backdoorbox, is pointer only (licence: GPL-2.0) · get_code("c70af6aa43a490cb")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

IBD_PSC Not yet run
unverified (harvested, no recorded run)
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("91fac429b14b8dc1")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_seed_worker Not yet run
unverified (harvested, no recorded run)
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("2829fcd1f540902b")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

_test Not yet run
unverified (harvested, no recorded run)
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("fa250ca519fc627c")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

test Not yet run
unverified (harvested, no recorded run)
thuyimingli/backdoorbox/core/defenses/IBD_PSC.py
pointer only (licence: GPL-2.0) · get_code("4689f052cb4bdf86")
How it ran

The body of this sample is withheld: GPL-2.0, as GitHub detects it on this paper's repository, thuyimingli/backdoorbox, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 3 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
accuracy
brick of this paper's assembly: helper
7 other papers
6 dated earlier, 1 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
2103.15798 (2021-03)
Rethinking Neural Operations for Diverse Tasks
2109.03508 (2021-09)
RepNAS: Searching for Efficient Re-parameterizing Blocks
and 4 more not named here
Base
brick of this paper's assembly: helper
1 other paper
1 later
2502.18508 (2025-02)
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Log
brick of this paper's assembly: helper
1 other paper
1 later · 1 only as an assembly brick
2502.18508 (2025-02)
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective inputlevel backdoor detection (dubbed IBD-PSC) as a 'firewall' to filter out malicious testing images. Our method is motivated by an intriguing phenomenon, i.e., parameter-oriented scaling consistency (PSC), where the prediction confidences of poisoned samples are significantly more consistent than those of benign ones when amplifying model parameters. In particular, we provide theoretical analysis to safeguard the foundations of the PSC phenomenon. We also design an adaptive method to select BN layers to scale up for effective detection. Extensive experiments are conducted on benchmark datasets, verifying the effectiveness and efficiency of our IBD-PSC method and its resistance to adaptive attacks. Codes are available at BackdoorBox.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2405.09786")
get_code_for_paper("2405.09786")
have("2405.09786")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2405.09786.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2405.09786.svg)](https://syntology.ai/paper/2405.09786)

Connect an agent — have() is free.