Papers › Adversarial Attack Generation Empowered by Min-Max Optimization

Adversarial Attack Generation Empowered by Min-Max Optimization

9 Jun 2019NeurIPS 2021 12arXiv:1906.03563archive 2025-07-28

Jingkang Wang, Tianyun Zhang, Sijia Liu, Pin-Yu Chen, Jiacen Xu, Makan Fardad, Bo Li

The worst-case training principle that minimizes the maximal adversarial loss, also known as adversarial training (AT), has shown to be a state-of-the-art approach for enhancing adversarial robustness. Nevertheless, min-max optimization beyond the purpose of AT has not been rigorously explored in the adversarial context. In this paper, we show how a general framework of min-max optimization over multiple domains can be leveraged to advance the design of different types of adversarial attacks. In particular, given a set of risk sources, minimizing the worst-case attack loss can be reformulated as a min-max problem by introducing domain weights that are maximized over the probability simplex of the domain set. We showcase this unified framework in three attack generation problems -- attacking model ensembles, devising universal perturbation under multiple inputs, and crafting attacks resilient to data transformations. Extensive experiments demonstrate that our approach leads to substantial attack improvement over the existing heuristic strategies as well as robustness improvement over state-of-the-art defense methods trained to be robust against multiple perturbation types. Furthermore, we find that the self-adjusted domain weights learned from our min-max framework can provide a holistic tool to explain the difficulty level of attack across domains. Code is available at https://github.com/wangjksjtu/minmax-adv.

PaperPDFConference PDFCodeCode Syntology ran

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 25 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 25 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

wangjksjtu/minmax-adv officialmentioned in papermentioned on GitHubpytorchMITSyntology: 25 samples, 11 ran (0 instrument-failed) · 14 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

25 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 14 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 · violated contract
10ran
14unverified

Licence: 0 of the 25 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 wangjksjtu/minmax-adv. “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. 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.

wangjksjtu/minmax-adv official repository 25 samples, 11 ran (0 instrument-failed) · 14 unverified
cw_loss in 5 papers neurips21/attacks/minmax.py ran MIT (permissive) · 936c00f08008f28d · report fixture: signature labels:SymbolicTensor/2/float, logits:SymbolicTensor/2/float, confidence:int/0/int · returned EagerTensor · level recorded 2026-09-25
get_interval neurips21/utils.py ran MIT (permissive) · f572fa6a26eff62d · report fixture: signature eps_l:float/0/float, eps_r:float/0/float, num:int/0/int · returned list · level recorded 2026-09-25
get_models in 11 papers neurips21/ens_attack.py ran MIT (permissive) · 8d68ad2ec3439b5c · report fixture: signature modelzoo:MockModelZoo/0/?, archs:list/1/str · returned list · level recorded 2026-09-25
identity in 174 papers
census: 11 implementations from 39 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
neurips21/utils.py ran MIT (permissive) · 22ad888be68bfa1b · report fixture: signature images:ndarray/4/float · returned EagerTensor · level recorded 2026-09-25
image_folder_custom_label pytorch/utils.py ran MIT (permissive) · 83e7640948d1e7ea · report fixture: signature root:str/0/str, transform:callable/0/?, idx2label:list/1/str · returned ImageFolder · level recorded 2026-09-25
l2_distance in 10 papers pytorch/utils.py ran MIT (permissive) · e9de120c9fccad8d · report fixture: signature model:callable/0/?, images:Tensor/2/float, adv_images:Tensor/2/float, labels:Tensor/1/int, device:str/0/str · returned Tensor · level recorded 2026-09-25
make_ens_minmax neurips21/ens_attack.py ran MIT (permissive) · ff4af237f270b266 · report fixture: signature sess:MockSession/0/?, env:MockEnv/0/?, X_data:ndarray/2/float, K:int/0/int, epochs:int/0/int, eps:float/0/float, batch_size:int/0/int · returned tuple · level recorded 2026-09-25
make_minmax_eot neurips21/trans_attack.py ran MIT (permissive) · 445cb63b8dd7ebb7 · report fixture: signature sess:MockSession/0/?, env:MockEnv/0/?, X_data:ndarray/2/float, epochs:int/0/int, eps:float/0/float, batch_size:int/0/int · returned ndarray · level recorded 2026-09-25
proj_box_appro neurips21/attacks/utils.py ran MIT (permissive) · 24a5cabdc0b7b91c · report fixture: signature v:EagerTensor/4/float, eps:float/0/float, p:int/0/int · returned EagerTensor · level recorded 2026-09-25
proj_prob_simplex neurips21/attacks/utils.py ran MIT (permissive) · 964d413db2fdd014 · report fixture: signature W:EagerTensor/2/float, batch_size:int/0/int, K:int/0/int · returned EagerTensor · level recorded 2026-09-25
str2bool in 533 papers neurips21/utils.py ran · violated contract MIT (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
evaluate in 514 papers neurips21/ens_attack.py unverified MIT (permissive) · 213267d02b7820b8 · report
evaluate in 514 papers neurips21/trans_attack.py unverified MIT (permissive) · e607dfc06f869a5d · report
evaluate in 514 papers neurips21/uni_attack.py unverified MIT (permissive) · 247982bef8192964 · report
fgm in 5 papers neurips21/attacks/fast_gradient.py unverified MIT (permissive) · 3ed5f9dfac95521e · report
fgmt neurips21/attacks/fast_gradient.py unverified MIT (permissive) · cd6509a1aade295c · report
get_model in 368 papers pytorch/ens_attack.py unverified MIT (permissive) · 1d6df60e31ef00c5 · report
make_uni_minmax neurips21/uni_attack.py unverified MIT (permissive) · 232ff7a5fe7a603e · report
minmax_ens neurips21/attacks/minmax.py unverified MIT (permissive) · 647f2c2e24c1966b · report
minmax_uni neurips21/attacks/minmax.py unverified MIT (permissive) · 8b57098358df5568 · report
modelA neurips21/models.py unverified MIT (permissive) · d8f5f464cb0707b2 · report
modelB neurips21/models.py unverified MIT (permissive) · d9e789eb6c5505bc · report
modelC neurips21/models.py unverified MIT (permissive) · 4e8ba12a7a587e76 · report
pgd in 18 papers neurips21/attacks/pgd.py unverified MIT (permissive) · fed551f077ea431d · report
proj_box neurips21/attacks/utils.py unverified MIT (permissive) · 8bf68b71ad3a0000 · report

Tasks

Adversarial AttackAdversarial Robustness

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