Papers › Self-supervised Adversarial Training of Monocular Depth Estimation against...

Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks

9 Jun 2024arXiv:2406.05857archive 2025-07-28

Zhiyuan Cheng, Cheng Han, James Liang, Qifan Wang, Xiangyu Zhang, Dongfang Liu

Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L_0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.

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 17 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 3 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 11 ran (9 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 11 samples that ran have no recorded date.

Bob-cheng/DepthModelHardening officialmentioned in paperpytorchMITSyntology: 17 samples, 11 ran (2 instrument-failed) · 6 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

17 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 3 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
3ran · violated contract
2ran; the contract check could not run
2ran
6unverified

Licence: 1 of the 17 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 Bob-cheng/DepthModelHardening. “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.

Bob-cheng/DepthModelHardening official repository 17 samples, 11 ran (2 instrument-failed) · 6 unverified
batch_post_process_disparity in 21 papers DepthNetworks/monodepth2/evaluate_depth.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · a8814cc5c348b987 · report fixture: signature l_disp:ndarray/3/float, r_disp:ndarray/3/float · returned ndarray · level recorded, date not recorded
compute_ate DepthNetworks/depth-hints/evaluate_pose.py ran · honoured contract fingerprinted MIT (permissive) · cccc24a3d20a9987 · report fixture: signature gtruth_xyz:ndarray/2/float, pred_xyz_o:ndarray/2/float · returned float32 · level recorded 2026-09-24
compute_errors in 41 papers DepthNetworks/monodepth2/evaluate_depth.py ran · violated contract fingerprinted MIT (permissive) · 71a2780a460fb55e · report fixture: signature gt:ndarray/2/float, pred:ndarray/2/float, mask:ndarray/2/float · returned tuple · level recorded, date not recorded
compute_errors in 41 papers DepthNetworks/depth-hints/evaluate_depth_old.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · edd4f86e8f02732f · report fixture: signature gt:ndarray/2/float, pred:ndarray/2/float · returned tuple · level recorded 2026-09-22
disp_to_depth in 21 papers depth_model.py ran · violated contract MIT (permissive) · 62287188376f0ba0 · report fixture: signature disp:Tensor/3/float, min_depth:float/0/float, max_depth:float/0/float · returned tuple · level recorded 2026-09-24
disp_to_depth in 21 papers my_utils.py ran · violated contract MIT (permissive) · 5ddbb1ceaa5ee4e9 · report fixture: signature disp:Tensor/3/float, min_depth:float/0/float, max_depth:float/0/float · returned tuple · level recorded 2026-09-24
dump_xyz DepthNetworks/depth-hints/evaluate_pose.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 0881d8bc3d8f6958 · report fixture: signature source_to_target_transformations:list/1/ndarray · returned list · level recorded 2026-09-24
get_mean_depth_diff my_utils.py ran MIT (permissive) · dde6b59baec616a6 · report fixture: signature adv_disp1:Tensor/3/float, ben_disp2:Tensor/3/float, scene_car_mask:Tensor/3/float, use_abs:bool/0/bool · returned Tensor · level recorded 2026-09-24
lin_interp dataLoader.py ran · honoured contract fingerprinted MIT (permissive) · deb9787d1bb70773 · report fixture: signature sparse_depth:ndarray/2/float · returned ndarray · level recorded 2026-09-24
load_and_preprocess_intrinsics depth_model.py ran · honoured contract MIT (permissive) · 15cbf0f1a95fa7c0 · report fixture: signature intrinsics_path:str/0/str, resize_width:int/0/int, resize_height:int/0/int · returned tuple · level recorded 2026-09-24
readPathFiles dataLoader.py ran MIT (permissive) · 28f0d87414159ae0 · report fixture: signature root_dir:str/0/str, list_name:str/0/str · returned list · level recorded 2026-09-24
eval_depth_diff my_utils.py unverified MIT (permissive) · 70e2744feb71bee5 · report
import_depth_model depth_model.py unverified MIT (permissive) · 5fd18fbd334c67fe · report
pil_loader in 144 papers dataLoader.py unverified MIT (permissive) · 803f2bd90f370619 · report
process_car_img image_preprocess.py unverified MIT (permissive) · 1c9e00a872e5f1ca · report
process_img in 6 papers image_preprocess.py unverified MIT (permissive) · 15fe5d7084a8f164 · report
process_mask image_preprocess.py unverified MIT (permissive) · 3cafefe1573485fd · report

Tasks

Adversarial RobustnessAutonomous DrivingContrastive LearningDepth EstimationMonocular Depth Estimation

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