Papers › Shape-invariant 3D Adversarial Point Clouds

Shape-invariant 3D Adversarial Point Clouds

8 Mar 2022CVPR 2022 1arXiv:2203.04041archive 2025-07-28

Qidong Huang, Xiaoyi Dong, Dongdong Chen, Hang Zhou, Weiming Zhang, Nenghai Yu

Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers, since they just involve an "implicit constrain" like global distance loss in the time-consuming optimization to limit the generated noise. While point cloud is a highly structured data format, it is hard to constrain its perturbation with a simple loss or metric properly. In this paper, we propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations. This map reveals the vulnerability of point cloud recognition models when encountering shape-invariant adversarial noises. These noises are designed along the shape surface with an "explicit constrain" instead of extra distance loss. Specifically, we first apply a reversible coordinate transformation on each point of the point cloud input, to reduce one degree of point freedom and limit its movement on the tangent plane. Then we calculate the best attacking direction with the gradients of the transformed point cloud obtained on the white-box model. Finally we assign each point with a non-negative score to construct the sensitivity map, which benefits both white-box adversarial invisibility and black-box query-efficiency extended in our work. Extensive evaluations prove that our method can achieve the superior performance on various point cloud recognition models, with its satisfying adversarial imperceptibility and strong resistance to different point cloud defense settings. Our code is available at: https://github.com/shikiw/SI-Adv.

PaperPDFConference PDFCodeCode 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="2203.04041")

Code

Syntology Ran 14 of 19 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 6 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 19 samples from 1 repository, 14 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shikiw/si-adv officialmentioned in papermentioned on GitHubpytorchMIT 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; 14 ran; 2 honoured the contract we drafted; 5 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
1ran · violated contract
6ran · fixture could not drive it
5ran
5unverified

Licence: 0 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 shikiw/SI-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. “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.

index_points shikiw/SI-Adv/model_utils/pct_util.py official repository ran · fixture could not drive it MIT (permissive) · 449a0265144f6530 · report
cal_loss shikiw/SI-Adv/model_utils/pct_util.py official repository ran · fixture could not drive it MIT (permissive) · c6c2758c0c2fa756 · report
closest_pool shikiw/SI-Adv/model_utils/kpconv_util.py official repository ran MIT (permissive) · 728888ce9772c062 · report
gather shikiw/SI-Adv/model_utils/kpconv_util.py official repository ran · fixture could not drive it MIT (permissive) · 06eb9b038422a6ef · report
get_scorenet_input shikiw/SI-Adv/model_utils/paconv_util.py official repository ran MIT (permissive) · d77f00230e16006d · report
index_points shikiw/SI-Adv/model_utils/pointconv_util.py official repository ran · fixture could not drive it MIT (permissive) · 573cb024ea47999f · report
knn shikiw/SI-Adv/model_utils/curvenet_util.py official repository ran fingerprinted MIT (permissive) · fd43b3106ac73716 · report
knn shikiw/SI-Adv/model_utils/paconv_util.py official repository ran fingerprinted MIT (permissive) · 69845e3c207ea9e7 · report
normal_knn shikiw/SI-Adv/model_utils/curvenet_util.py official repository ran fingerprinted MIT (permissive) · 1979f86a5b2b0446 · report
pc_normalize shikiw/SI-Adv/data_utils/ModelNetDataLoader.py official repository ran · honoured contract fingerprinted MIT (permissive) · 4783fbece52f500e · report
pc_normalize shikiw/SI-Adv/model_utils/curvenet_util.py official repository ran · honoured contract fingerprinted MIT (permissive) · ec413739d406e611 · report
radius_gaussian shikiw/SI-Adv/model_utils/kpconv_util.py official repository ran · violated contract MIT (permissive) · 42f2cd40ba483d3b · report
square_distance shikiw/SI-Adv/model_utils/pct_util.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3bfe172e686075cd · report
square_distance shikiw/SI-Adv/model_utils/pointconv_util.py official repository ran · fixture could not drive it MIT (permissive) · 580dee6761649b29 · report
assign_score_withk shikiw/SI-Adv/cuda_lib/functional.py official repository unverified MIT (permissive) · 72e38b49e5bad8ba · report
assign_score_withk_halfkernel shikiw/SI-Adv/cuda_lib/functional.py official repository unverified MIT (permissive) · f6e6c6c45d23680a · report
farthest_point_sample shikiw/SI-Adv/data_utils/ModelNetDataLoader.py official repository unverified MIT (permissive) · f80066a00e7156a2 · report
feat_trans_dgcnn shikiw/SI-Adv/model_utils/paconv_util.py official repository unverified MIT (permissive) · 5fb9a68241c62149 · report
timeit shikiw/SI-Adv/model_utils/pointconv_util.py official repository unverified MIT (permissive) · b1227ddb721e2999 · report

Tasks

Sensitivity

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