Papers › Learning to Transform Dynamically for Better Adversarial Transferability

Learning to Transform Dynamically for Better Adversarial Transferability

23 May 2024CVPR 2024 1arXiv:2405.14077archive 2025-07-28

Rongyi Zhu, Zeliang Zhang, Susan Liang, Zhuo Liu, Chenliang Xu

Adversarial examples, crafted by adding perturbations imperceptible to humans, can deceive neural networks. Recent studies identify the adversarial transferability across various models, i.e., the cross-model attack ability of adversarial samples. To enhance such adversarial transferability, existing input transformation-based methods diversify input data with transformation augmentation. However, their effectiveness is limited by the finite number of available transformations. In our study, we introduce a novel approach named Learning to Transform (L2T). L2T increases the diversity of transformed images by selecting the optimal combination of operations from a pool of candidates, consequently improving adversarial transferability. We conceptualize the selection of optimal transformation combinations as a trajectory optimization problem and employ a reinforcement learning strategy to effectively solve the problem. Comprehensive experiments on the ImageNet dataset, as well as practical tests with Google Vision and GPT-4V, reveal that L2T surpasses current methodologies in enhancing adversarial transferability, thereby confirming its effectiveness and practical significance. The code is available at https://github.com/RongyiZhu/L2T.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples: 18 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 19: 12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); found in paper text by Syntology: 14 samples from 1 repository, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed); 1 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.

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.

rongyizhu/l2t officialmentioned in paperpytorchSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 unverified 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

19 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
1ran; the contract check could not run
9ran
7unverified

Licence: 5 of the 19 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. 1 sample is 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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

rongyizhu/l2t official repository 4 samples, 1 ran (0 instrument-failed) · 3 unverified
ssm in 8 papers l2t.py ran no licence file found · pointer only · 66827411a5708f30 · report fixture: returned ssm · level recorded 2026-09-22
Attack in 15 papers l2t.py unverified no licence file found · pointer only · 27a0edca5630cc99 · report
L2T l2t.py unverified no licence file found · pointer only · e810c2cac2611d1d · report
RWAug_Search l2t.py unverified no licence file found · pointer only · 73cfc6839c8a87e5 · report
ZhangAIPI/TransferAttack found in paper text by Syntology 14 samples, 10 ran (1 instrument-failed) · 4 unverified
affine in 7 papers transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · 76ec6ea1c611aa1b · report fixture: returned affine · level recorded 2026-09-22
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · 3270095b250d07ba · report fixture: returned crop · level recorded 2026-09-22
dim in 5 papers transferattack/input_transformation/l2t.py ran MIT (permissive) · 7a38c7f0ecdc2bb8 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ide transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · 98e0628573515149 · report fixture: returned ide · level recorded 2026-09-22
masked transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · 7882898c7bd1f8d5 · report fixture: returned masked · level recorded 2026-09-22
rotate in 56 papers transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · 8b44d6dad87b7938 · report fixture: returned rotate · level recorded 2026-09-22
select_op transferattack/input_transformation/l2t.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 28ce88cbcad7b395 · report fixture: signature op_params:Tensor/1/float, num_ops:int/0/int · returned list · level recorded 2026-09-22
sim in 14 papers transferattack/input_transformation/l2t.py ran fingerprinted MIT (permissive) · b7715794a192878f · report fixture: returned sim · level recorded 2026-09-22
ssm in 8 papers transferattack/input_transformation/l2t.py ran MIT (permissive) · d0569b886ab791b6 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
trace_prob transferattack/input_transformation/l2t.py ran · violated contract MIT (permissive) · 29e23c69b7369fa0 · report fixture: signature op_params:Tensor/1/float, op_ids:list/1/int · returned Tensor · level recorded 2026-09-22
L2T transferattack/input_transformation/l2t.py unverified MIT (permissive) · 09ad6d82e0bfd17e · report
RWAug_Search transferattack/input_transformation/l2t.py unverified MIT (permissive) · 1c20a036849844e1 · report
admix transferattack/input_transformation/l2t.py unverified MIT (permissive) · eb6887fb7eb0a115 · report
blockshuffle transferattack/input_transformation/l2t.py unverified MIT (permissive) · fc8d40755d69834d · report
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is 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.
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 9910e2fc297f8665 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22

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. 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Learning to Transform (L2T) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Learning to Transform (L2T) (graph method: Learning to Transform (L2T)). 16 bricks; individually on a fixture: 11 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. L2T entry · level 0 · unverified · 09ad6d82e0bfd17e
  2. Attack helper · level 0 · unverified · 01110864c3d8eec8
  3. RWAug_Search helper · level 0 · unverified · 1c20a036849844e1
  4. select_op helper · level 1 · ran; the contract check could not run (RAISES) · 28ce88cbcad7b395
  5. trace_prob helper · level 1 · ran · violated contract · 29e23c69b7369fa0
  6. admix data_transform · level 0 · unverified · eb6887fb7eb0a115
  7. affine data_transform · level 1 · ran · 76ec6ea1c611aa1b
  8. blockshuffle data_transform · level 0 · unverified · fc8d40755d69834d
  9. crop data_transform · level 1 · ran · 3270095b250d07ba
  10. dim data_transform · level 1 · ran · 7a38c7f0ecdc2bb8
  11. ide data_transform · level 1 · ran · 98e0628573515149
  12. identity data_transform · level 1 · ran · honoured contract · 9910e2fc297f8665
  13. masked data_transform · level 1 · ran · 7882898c7bd1f8d5
  14. rotate data_transform · level 1 · ran · 8b44d6dad87b7938
  15. sim data_transform · level 1 · ran · b7715794a192878f
  16. ssm data_transform · level 1 · ran · d0569b886ab791b6

harvested Assembly for Learning to Transform (L2T) (graph method: Learning to Transform (L2T)). 16 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. L2T entry · level 0 · unverified · e810c2cac2611d1d
  2. Attack model · level 0 · unverified · 27a0edca5630cc99
  3. RWAug_Search helper · level 0 · unverified · 73cfc6839c8a87e5
  4. select_op sampler · level 1 · ran; the contract check could not run (RAISES) · 28ce88cbcad7b395
  5. trace_prob sampler · level 1 · ran · violated contract · 29e23c69b7369fa0
  6. admix data_transform · level 0 · unverified · eb6887fb7eb0a115
  7. affine data_transform · level 1 · ran · 76ec6ea1c611aa1b
  8. blockshuffle data_transform · level 0 · unverified · fc8d40755d69834d
  9. crop data_transform · level 1 · ran · 3270095b250d07ba
  10. dim data_transform · level 1 · ran · 7a38c7f0ecdc2bb8
  11. ide data_transform · level 1 · ran · 98e0628573515149
  12. identity data_transform · level 1 · ran · honoured contract · 9910e2fc297f8665
  13. masked data_transform · level 1 · ran · 7882898c7bd1f8d5
  14. rotate data_transform · level 1 · ran · 8b44d6dad87b7938
  15. sim data_transform · level 1 · ran · b7715794a192878f
  16. ssm data_transform · level 1 · ran · 66827411a5708f30

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="2405.14077") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Diversity

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