SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.07863 · ICLR · 2024

Backdoor Contrastive Learning via Bi-level Trigger Optimization

Hao Lu, Jinghui Chen, Lu Lin, Ting Wang, Xinyu Zhang, Yingcong Chen, Weiyu Sun

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 3 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/2404.07863.json · badge: /api/ran/2404.07863.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
swy666/ssl-backdoor-blto canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
SWY666/SSL-backdoor-BLTO canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
FunctionStatusWhere it lives
D Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SWY666/SSL-backdoor-BLTO/Dirty_code_for_attack/models/simsiam.py
pointer only (licence: NONE) · get_code("b2429807c9efa3f7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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.

D_PCA Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
SWY666/SSL-backdoor-BLTO/Dirty_code_for_attack/models/simsiam.py
pointer only (licence: NONE) · get_code("b7925a42dfb0fae6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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.

NT_XentLoss Ran
ran; our contract draft was wrong, not the code
SWY666/SSL-backdoor-BLTO/Dirty_code_for_attack/models/simclr.py
pointer only (licence: NONE) · get_code("5dec8f84e0dfd0c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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.

apply_generatorG Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
swy666/ssl-backdoor-blto/Trigger/Generator_from_TTA/Generate_CIAFR10_using_TTA_origin.py
pointer only (licence: NONE) · get_code("a12eecb0fd926bd4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, swy666/ssl-backdoor-blto when it was checked. 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.

apply_generatorG Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
swy666/ssl-backdoor-blto/Dirty_code_for_attack/Simsiam_backdoor_eval.py
pointer only (licence: NONE) · get_code("e78b4c1f05d87a86")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, swy666/ssl-backdoor-blto when it was checked. 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.

normalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
swy666/ssl-backdoor-blto/Dirty_code_for_attack/Simsiam_backdoor_eval.py
pointer only (licence: NONE) · get_code("5e6a53c98adae9a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, swy666/ssl-backdoor-blto when it was checked. 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.

optimize_netG Ran
ran; our contract draft was wrong, not the code
swy666/ssl-backdoor-blto/Dirty_code_for_attack/Simsam_min_min_Official_finetune_target_EoT.py
pointer only (licence: NONE) · get_code("25735bb58aee10b7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, swy666/ssl-backdoor-blto when it was checked. 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.

step_iteration Ran
ran; our contract draft was wrong, not the code
swy666/ssl-backdoor-blto/Dirty_code_for_attack/Simsiam_backdoor_eval.py
pointer only (licence: NONE) · get_code("82bfd431649f7cb2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, swy666/ssl-backdoor-blto when it was checked. 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.

get_args Not yet run
unverified (harvested, no recorded run)
SWY666/SSL-backdoor-BLTO/Dirty_code_for_attack/arguments.py
pointer only (licence: NONE) · get_code("ca84b508354783c3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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.

get_args_multidistribute Not yet run
unverified (harvested, no recorded run)
SWY666/SSL-backdoor-BLTO/Dirty_code_for_attack/arguments.py
pointer only (licence: NONE) · get_code("184bc3aa05cbcb7f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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.

get_ctrl_offline Not yet run
unverified (harvested, no recorded run)
SWY666/SSL-backdoor-BLTO/Dataset/CTRL_offline.py
pointer only (licence: NONE) · get_code("baeed5164d5bb57f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, SWY666/SSL-backdoor-BLTO when it was checked. 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 10 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
D 5 other papers
4 dated earlier, 1 later
2011.10566 (2020-11)
Exploring Simple Siamese Representation Learning
2105.00470 (2021-05)
On Feature Decorrelation in Self-Supervised Learning
2110.08406 (2021-10)
Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
and 2 more not named here

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

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack target class, thus fooling the downstream predictor to misclassify it as the target. Existing attacks usually adopt a fixed trigger pattern and poison the training set with trigger-injected data, hoping for the feature extractor to learn the association between trigger and target class. However, we find that such fixed trigger design fails to effectively associate trigger-injected data with target class in the embedding space due to special CL mechanisms, leading to a limited attack success rate (ASR). This phenomenon motivates us to find a better backdoor trigger design tailored for CL framework. In this paper, we propose a bi-level optimization approach to achieve this goal, where the inner optimization simulates the CL dynamics of a surrogate victim, and the outer optimization enforces the backdoor trigger to stay close to the target throughout the surrogate CL procedure. Extensive experiments show that our attack can achieve a higher attack success rate (e.g., 99% ASR on ImageNet-100) with a very low poisoning rate (1%). Besides, our attack can effectively evade existing state-of-the-art defenses. Code is available at: https://github.com/SWY666/SSL-backdoor-BLTO.

For agents

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

get_harvested_code_for_paper("2404.07863")
get_code_for_paper("2404.07863")
have("2404.07863")

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

curl https://syntology.ai/api/ran/2404.07863.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.07863.svg)](https://syntology.ai/paper/2404.07863)

Connect an agent — have() is free.