Papers › Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

26 Mar 2024CVPR 2024 1arXiv:2403.17301archive 2025-07-28

Junhao Zheng, Chenhao Lin, Jiahao Sun, Zhengyu Zhao, Qian Li, Chao Shen

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patches, so they only affect a small, localized region in the MDE map but fail under various viewpoints. To address these limitations, we propose 3D Depth Fool (3D²Fool), the first 3D texture-based adversarial attack against MDE models. 3D²Fool is specifically optimized to generate 3D adversarial textures agnostic to model types of vehicles and to have improved robustness in bad weather conditions, such as rain and fog. Experimental results validate the superior performance of our 3D²Fool across various scenarios, including vehicles, MDE models, weather conditions, and viewpoints. Real-world experiments with printed 3D textures on physical vehicle models further demonstrate that our 3D²Fool can cause an MDE error of over 10 meters.

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="2403.17301")

Code

Syntology Ran 13 of 13 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 13 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gandolfczjh/3d2fool officialmentioned in papermentioned 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

13 samples harvested; 13 ran; 0 honoured the contract we drafted; 0 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.

13ran

Licence: 13 of the 13 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 Gandolfczjh/3D2Fool. “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.

disp_to_depth Gandolfczjh/3D2Fool/layers.py official repository ran no licence file found · pointer only · 62287188376f0ba0 · report
disp_to_depth Gandolfczjh/3D2Fool/attack_base.py official repository ran no licence file found · pointer only · 5ddbb1ceaa5ee4e9 · report
get_affected_ratio Gandolfczjh/3D2Fool/attack_base.py official repository ran no licence file found · pointer only · f384289107aec65d · report
get_mean_depth_diff Gandolfczjh/3D2Fool/attack_base.py official repository ran no licence file found · pointer only · 544b68db9c9f5039 · report
get_translation_matrix Gandolfczjh/3D2Fool/layers.py official repository ran fingerprinted no licence file found · pointer only · 955112f5788539a8 · report
load_velodyne_points Gandolfczjh/3D2Fool/kitti_utils.py official repository ran no licence file found · pointer only · 8bfc895e86bfc7bc · report
normalize_image Gandolfczjh/3D2Fool/utils.py official repository ran fingerprinted no licence file found · pointer only · 332a1ab65ab9e5a1 · report
read_calib_file Gandolfczjh/3D2Fool/kitti_utils.py official repository ran no licence file found · pointer only · ff833c099a80a327 · report
readlines Gandolfczjh/3D2Fool/utils.py official repository ran no licence file found · pointer only · 859a6ec5fa262fcb · report
resnet_multiimage_input Gandolfczjh/3D2Fool/networks/resnet_encoder.py official repository ran no licence file found · pointer only · ab7c813560099f29 · report
sec_to_hm Gandolfczjh/3D2Fool/utils.py official repository ran fingerprinted no licence file found · pointer only · a340a99b831a7368 · report
sub2ind Gandolfczjh/3D2Fool/kitti_utils.py official repository ran no licence file found · pointer only · 04e9b96b63844176 · report
transformation_from_parameters Gandolfczjh/3D2Fool/layers.py official repository ran no licence file found · pointer only · cdc03d6bfc4d3a34 · report

Tasks

Adversarial AttackAutonomous DrivingDepth 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