Papers › GenAttack: Practical Black-box Attacks with Gradient-Free Optimization

GenAttack: Practical Black-box Attacks with Gradient-Free Optimization

28 May 2018arXiv:1805.11090archive 2025-07-28

Moustafa Alzantot, Yash Sharma, Supriyo Chakraborty, huan zhang, Cho-Jui Hsieh, Mani Srivastava

Deep neural networks are vulnerable to adversarial examples, even in the black-box setting, where the attacker is restricted solely to query access. Existing black-box approaches to generating adversarial examples typically require a significant number of queries, either for training a substitute network or performing gradient estimation. We introduce GenAttack, a gradient-free optimization technique that uses genetic algorithms for synthesizing adversarial examples in the black-box setting. Our experiments on different datasets (MNIST, CIFAR-10, and ImageNet) show that GenAttack can successfully generate visually imperceptible adversarial examples against state-of-the-art image recognition models with orders of magnitude fewer queries than previous approaches. Against MNIST and CIFAR-10 models, GenAttack required roughly 2,126 and 2,568 times fewer queries respectively, than ZOO, the prior state-of-the-art black-box attack. In order to scale up the attack to large-scale high-dimensional ImageNet models, we perform a series of optimizations that further improve the query efficiency of our attack leading to 237 times fewer queries against the Inception-v3 model than ZOO. Furthermore, we show that GenAttack can successfully attack some state-of-the-art ImageNet defenses, including ensemble adversarial training and non-differentiable or randomized input transformations. Our results suggest that evolutionary algorithms open up a promising area of research into effective black-box attacks.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1805.11090")

Code

Syntology Ran 2 of 12 code samples harvested from 2 repositories linked to this paper; 10 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: official repository: 9 samples from 1 repository, 2 ran; community (archive-listed): 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nesl/adversarial_genattack officialmentioned in papermentioned on GitHubtfMIT report
maremun/GenAttackMCS2018 mentioned on GitHubpytorch 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

12 samples harvested; 2 ran; 2 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
10unverified

Licence: 0 of the 12 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

extract_data nesl/adversarial_genattack/setup_mnist.py official repository ran · honoured contract MIT (permissive) · 86c9fa246614e9a9 · report
extract_labels nesl/adversarial_genattack/setup_mnist.py official repository ran · honoured contract MIT (permissive) · a0cf6bb81ff7819e · report
generate_data nesl/adversarial_genattack/utils.py official repository unverified MIT (permissive) · bb5e83c39bdec690 · report
l_2_dist nesl/adversarial_genattack/utils.py official repository unverified MIT (permissive) · 32ecbd87f915e308 · report
l_inf_dist nesl/adversarial_genattack/utils.py official repository unverified MIT (permissive) · 6f056b1dd2976681 · report
load_batch nesl/adversarial_genattack/setup_cifar.py official repository unverified MIT (permissive) · ab7faf0047f2c872 · report
load_batch nesl/adversarial_genattack/setup_cifar.py official repository unverified MIT (permissive) · 3b4fb87c66244ebf · report
readimg nesl/adversarial_genattack/setup_inception.py official repository unverified MIT (permissive) · 59c8c9a8f20e44a9 · report
train nesl/adversarial_genattack/train_models.py official repository unverified MIT (permissive) · 8b389eb9f5726984 · report
crossover maremun/GenAttackMCS2018/genattack.py community (archive-listed) unverified MIT (permissive) · d0d8c5d6a3a88cd8 · report
get_mutation maremun/GenAttackMCS2018/genattack.py community (archive-listed) unverified MIT (permissive) · ec5f90b9679633c5 · report
where maremun/GenAttackMCS2018/genattack.py community (archive-listed) unverified MIT (permissive) · 23e2e9ee651bbb83 · report

Tasks

Adversarial AttackAdversarial RobustnessEvolutionary Algorithms

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAuxiliary ClassifierAverage PoolingConvolutionDense ConnectionsDropoutInception-v3Inception-v3 ModuleLabel SmoothingMax PoolingRMSPropSoftmax

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