Papers › NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against...

NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations

10 Jun 2023arXiv:2306.06359archive 2025-07-28

Yonggan Fu, Ye Yuan, Souvik Kundu, Shang Wu, Shunyao Zhang, Yingyan Celine Lin

Generalizable Neural Radiance Fields (GNeRF) are one of the most promising real-world solutions for novel view synthesis, thanks to their cross-scene generalization capability and thus the possibility of instant rendering on new scenes. While adversarial robustness is essential for real-world applications, little study has been devoted to understanding its implication on GNeRF. We hypothesize that because GNeRF is implemented by conditioning on the source views from new scenes, which are often acquired from the Internet or third-party providers, there are potential new security concerns regarding its real-world applications. Meanwhile, existing understanding and solutions for neural networks' adversarial robustness may not be applicable to GNeRF, due to its 3D nature and uniquely diverse operations. To this end, we present NeRFool, which to the best of our knowledge is the first work that sets out to understand the adversarial robustness of GNeRF. Specifically, NeRFool unveils the vulnerability patterns and important insights regarding GNeRF's adversarial robustness. Built upon the above insights gained from NeRFool, we further develop NeRFool+, which integrates two techniques capable of effectively attacking GNeRF across a wide range of target views, and provide guidelines for defending against our proposed attacks. We believe that our NeRFool/NeRFool+ lays the initial foundation for future innovations in developing robust real-world GNeRF solutions. Our codes are available at: https://github.com/GATECH-EIC/NeRFool.

PaperPDFCodeCode 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 harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 14 ran (4 with no instrument failure; 10 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 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.

gatech-eic/nerfool officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 14 ran (10 instrument-failed) · 5 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: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 5 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.

2ran · honoured contract
5ran · our draft was wrong
5ran; the contract check could not run
2ran
5unverified

Licence: 3 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from gatech-eic/nerfool. “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.

gatech-eic/nerfool official repository 19 samples, 14 ran (10 instrument-failed) · 5 unverified
SL1Loss eval/ibrnet/eval_adv.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 375ac5d275e351d0 · report fixture: signature depth_pred:Tensor/3/float, depth_gt:Tensor/3/float, mask:NoneType/0/?, useMask:bool/0/bool · returned Tensor · level recorded 2026-09-22
calc_depth_smooth_loss eval/ibrnet/eval_adv.py ran · honoured contract MIT (permissive) · 5f62ab16341c86e9 · report fixture: signature ret:dict/0/?, patch_size:int/0/int, loss_type:str/0/str · returned Tensor · level recorded 2026-09-24
calc_depth_var eval/ibrnet/eval_adv.py ran · honoured contract MIT (permissive) · abd301e7de6eb76a · report fixture: signature ret:dict/0/? · returned Tensor · level recorded 2026-09-22
class_for_name in 6 papers gnt/feature_network.py ran · our draft was wrong MIT (permissive) · 22e670c8093b7c80 · report fixture: signature module_name:str/0/str, class_name:str/0/str · returned type · level recorded 2026-09-24
conv1x1 in 691 papers gnt/feature_network.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 036782aebf2185a0 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers gnt/feature_network.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7e558f4229d053af · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-22
dilate_img ibrnet/sample_ray.py ran MIT (permissive) · ffadd89803ecb27b · report fixture: signature img:ndarray/2/int, kernel_size:int/0/int · returned ndarray · level recorded 2026-09-24
fused_mean_variance in 6 papers ibrnet/mlp_network.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 34ea5f2db980a0f7 · report fixture: returned tuple · level recorded 2026-09-22
img2mse in 9 papers eval/ibrnet/eval_adv.py ran · our draft was wrong fingerprinted MIT (permissive) · 598359a17b0a3a7f · report fixture: signature x:Tensor/4/float, y:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-22
parse_camera eval/ibrnet/eval_adv.py ran; the contract check could not run (RAISES) MIT (permissive) · 3b75759486992d96 · report fixture: signature params:Tensor/2/float · returned tuple · level recorded 2026-09-22
project_with_depth eval/ibrnet/eval_adv.py ran; the contract check could not run (RAISES) MIT (permissive) · a4e9aa55fe6d49cd · report fixture: signature depth_ref:Tensor/3/float, intrinsics_ref:Tensor/3/float, extrinsics_ref:Tensor/3/float, intrinsics_src:Tensor/3/float, extrinsics_src:Tensor/3/float · returned tuple · level recorded 2026-09-24
raw2outputs in 7 papers eval/ibrnet/eval_adv.py ran; the contract check could not run (RAISES) MIT (permissive) · 1bbb09fcee81b67f · report fixture: signature raw:Tensor/3/float, z_vals:Tensor/2/float, mask:Tensor/2/int, white_bkgd:bool/0/bool, geo_noise:NoneType/0/? · returned OrderedDict · level recorded 2026-09-24
sample_along_camera_ray eval/ibrnet/eval_adv.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 1771162d12b6e77f · report fixture: signature ray_o:Tensor/2/float, ray_d:Tensor/2/float, depth_range:Tensor/2/float, N_samples:int/0/int, inv_uniform:bool/0/bool, det:bool/0/bool · returned tuple · level recorded 2026-09-22
sample_pdf in 37 papers eval/ibrnet/eval_adv.py ran · our draft was wrong MIT (permissive) · ca8853bb68d69984 · report fixture: signature bins:Tensor/2/float, weights:Tensor/2/float, N_samples:int/0/int, det:bool/0/bool · returned Tensor · level recorded 2026-09-22
RaySamplerSingleImage eval/ibrnet/eval_adv.py unverified MIT (permissive) · 80acb005a349e795 · report
de_parallel in 6 papers gnt/model.py unverified MIT (permissive) here; the stored copy is pointer only · b7b60558eb5ef908 · report
forward_warp eval/ibrnet/eval_adv.py unverified MIT (permissive) · ed70bc3a7a4fe74a · report
optimize_adv_perturb eval/ibrnet/eval_adv.py unverified MIT (permissive) · d861a166b8b9beb1 · report
render_rays in 7 papers eval/ibrnet/eval_adv.py unverified MIT (permissive) · be1957ada4055c7a · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for NeRFool (graph method: NeRFool). 13 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. optimize_adv_perturb entry · level 0 · unverified · d861a166b8b9beb1
  2. RaySamplerSingleImage helper · level 0 · unverified · 80acb005a349e795
  3. SL1Loss loss · level 1 · ran · 375ac5d275e351d0
  4. calc_depth_smooth_loss loss · level 1 · ran · honoured contract · 5f62ab16341c86e9
  5. calc_depth_var helper · level 1 · ran · honoured contract · abd301e7de6eb76a
  6. forward_warp helper · level 0 · unverified · ed70bc3a7a4fe74a
  7. img2mse helper · level 1 · ran · our draft was wrong · 598359a17b0a3a7f
  8. render_rays helper · level 0 · unverified · be1957ada4055c7a
  9. parse_camera helper · level 1 · ran; the contract check could not run (RAISES) · 3b75759486992d96
  10. project_with_depth helper · level 1 · ran; the contract check could not run (RAISES) · a4e9aa55fe6d49cd
  11. raw2outputs helper · level 1 · ran; the contract check could not run (RAISES) · 1bbb09fcee81b67f
  12. sample_along_camera_ray helper · level 1 · ran; the contract check could not run (RAISES) · 1771162d12b6e77f
  13. sample_pdf helper · level 1 · ran · our draft was wrong · ca8853bb68d69984

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="2306.06359") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Adversarial RobustnessNovel View Synthesis

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