Papers › RobFR: Benchmarking Adversarial Robustness on Face Recognition

RobFR: Benchmarking Adversarial Robustness on Face Recognition

8 Jul 2020arXiv:2007.04118archive 2025-07-28

Xiao Yang, Dingcheng Yang, Yinpeng Dong, Hang Su, Wenjian Yu, Jun Zhu

Face recognition (FR) has recently made substantial progress and achieved high accuracy on standard benchmarks. However, it has raised security concerns in enormous FR applications because deep CNNs are unusually vulnerable to adversarial examples, and it is still lack of a comprehensive robustness evaluation before a FR model is deployed in safety-critical scenarios. To facilitate a better understanding of the adversarial vulnerability on FR, we develop an adversarial robustness evaluation library on FR named RobFR, which serves as a reference for evaluating the robustness of downstream tasks. Specifically, RobFR involves 15 popular naturally trained FR models, 9 models with representative defense mechanisms and 2 commercial FR API services, to perform the robustness evaluation by using various adversarial attacks as an important surrogate. The evaluations are conducted under diverse adversarial settings in terms of dodging and impersonation, ℓ₂ and ℓ_∞, as well as white-box and black-box attacks. We further propose a landmark-guided cutout (LGC) attack method to improve the transferability of adversarial examples for black-box attacks by considering the special characteristics of FR. Based on large-scale evaluations, the commercial FR API services fail to exhibit acceptable performance on robustness evaluation, and we also draw several important conclusions for understanding the adversarial robustness of FR models and providing insights for the design of robust FR models. RobFR is open-source and maintains all extendable modules, i.e., Datasets, FR Models, Attacks&Defenses, and Evaluations at https://github.com/ShawnXYang/Face-Robustness-Benchmark, which will be continuously updated to promote future research on robust FR.

PaperPDFCodeCode 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 23 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 11 samples from 1 repository, 10 ran (8 with no instrument failure; 2 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

ShawnXYang/Face-Robustness-Benchmark officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 6 ran (0 instrument-failed) · 6 unverified report
thu-ml/realsafe mentioned on GitHubtfApache-2.0Syntology: 11 samples, 10 ran (2 instrument-failed) · 1 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

23 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 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.

2ran · our draft was wrong
14ran
7unverified

Licence: 0 of the 23 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. “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.

ShawnXYang/Face-Robustness-Benchmark official repository 12 samples, 6 ran (0 instrument-failed) · 6 unverified
get_dataset_celeb preprocess/align_methods/face_image.py ran Apache-2.0 (permissive) · 924034eebb04536f · report fixture: signature input_dir:str/0/str · returned list · level recorded 2026-09-25
get_dataset_webface preprocess/align_methods/face_image.py ran Apache-2.0 (permissive) · baa6487e16d2b4a8 · report fixture: signature input_dir:str/0/str · returned list · level recorded 2026-09-25
getlist_landmark RobFR/attack/face_landmark.py ran Apache-2.0 (permissive) · e7be7c2ad97b40fe · report fixture: signature names:list/1/str, landmark_values:dict/0/?, num_samples:int/0/int, img_shape:tuple/1/int, sigma:int/0/int · returned ndarray · level recorded 2026-09-25
layer in 12 papers preprocess/align_methods/detect_face.py ran Apache-2.0 (permissive) · fab32b621c712604 · report fixture: signature op:callable/0/? · returned function · level recorded 2026-09-25
load_property preprocess/align_methods/face_image.py ran Apache-2.0 (permissive) · a0e97123727a9fb0 · report fixture: signature data_dir:str/0/str · returned EasyDict · level recorded 2026-09-25
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
preprocess/align_methods/face_preprocess.py ran Apache-2.0 (permissive) · 1586a591b369e039 · report fixture: signature img:ndarray/3/int, image_size:tuple/1/int, bbox:NoneType/0/?, landmark:ndarray/2/float · returned tuple · level recorded 2026-09-25
create_mtcnn preprocess/align_methods/detect_face.py unverified Apache-2.0 (permissive) · edfa6042244eb012 · report
detect_face in 7 papers preprocess/align_methods/detect_face.py unverified Apache-2.0 (permissive) · 96bf1c60f74fc61d · report
draw_gaussian in 5 papers RobFR/attack/face_landmark.py unverified Apache-2.0 (permissive) · 37f16a7ffcbc8b0d · report
get_sample_landmark RobFR/attack/face_landmark.py unverified Apache-2.0 (permissive) · f894d169c2478af7 · report
parse_lst_line preprocess/align_methods/face_preprocess.py unverified Apache-2.0 (permissive) · 82b10a215c8cd30f · report
read_image in 73 papers preprocess/align_methods/face_preprocess.py unverified Apache-2.0 (permissive) · 79625c2830b046be · report
thu-ml/realsafe community (archive-listed) 11 samples, 10 ran (2 instrument-failed) · 1 unverified
build_loss_scaler ares/utils/loss.py ran Apache-2.0 (permissive) · 6b37094c7d0968d0 · report fixture: signature args:Args/0/?, _logger:Logger/0/? · returned tuple · level recorded 2026-09-24
conv1x1 in 691 papers ares/model/resnet.py ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers ares/model/resnet.py ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · 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, date not recorded
conv3x3 in 1,376 papers ares/model/resnet_denoise.py ran Apache-2.0 (permissive) · c4b3a9d234aede9e · 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 2026-09-24
filter_state_dict in 12 papers ares/model/cifar10_cls.py ran Apache-2.0 (permissive) · 68e05d78529d3a4b · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-24
get_url in 8 papers ares/model/cifar_model_zoo.py ran Apache-2.0 (permissive) · 152d421c48b6bfa2 · report fixture: signature ckpt_name:str/0/str · returned str · level recorded 2026-09-24
get_url in 8 papers ares/model/imagenet_model_zoo.py ran fingerprinted Apache-2.0 (permissive) · bb60872260d982f8 · report fixture: signature ckpt_name:str/0/str · returned str · level recorded 2026-09-24
loss_adv ares/utils/loss.py ran Apache-2.0 (permissive) · 3ce41c03fb062474 · report fixture: signature loss_name:str/0/str, outputs:Tensor/2/float, labels:Tensor/1/int, target_labels:Tensor/1/int, target:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-24
margin_loss in 13 papers ares/utils/loss.py ran Apache-2.0 (permissive) · b460ad8e4633515e · report fixture: signature outputs:Tensor/2/float, labels:Tensor/1/int, target_labels:Tensor/1/int, targeted:bool/0/bool, device:str/0/str · returned Tensor · level recorded 2026-09-24
tf_pad ares/model/resnet_denoise.py ran fingerprinted Apache-2.0 (permissive) · 6cbaa7427c406784 · report fixture: signature x:Tensor/4/float, kernel_size:int/0/int, stride:int/0/int · returned Tensor · level recorded 2026-09-24
resnet18 in 432 papers ares/model/resnet.py unverified Apache-2.0 (permissive) · 42e5e0701ba43b01 · report

Tasks

Adversarial RobustnessBenchmarkingFace Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Cutout

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