Papers › Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception...

Invisible for both Camera and LiDAR: Security of Multi-Sensor Fusion based Perception in Autonomous Driving Under Physical-World Attacks

17 Jun 2021arXiv:2106.09249archive 2025-07-28

Yulong Cao*, Ningfei Wang*, Chaowei Xiao*, Dawei Yang*, Jin Fang, Ruigang Yang, Qi Alfred Chen, Mingyan Liu, Bo Li

In Autonomous Driving (AD) systems, perception is both security and safety critical. Despite various prior studies on its security issues, all of them only consider attacks on camera- or LiDAR-based AD perception alone. However, production AD systems today predominantly adopt a Multi-Sensor Fusion (MSF) based design, which in principle can be more robust against these attacks under the assumption that not all fusion sources are (or can be) attacked at the same time. In this paper, we present the first study of security issues of MSF-based perception in AD systems. We directly challenge the basic MSF design assumption above by exploring the possibility of attacking all fusion sources simultaneously. This allows us for the first time to understand how much security guarantee MSF can fundamentally provide as a general defense strategy for AD perception. We formulate the attack as an optimization problem to generate a physically-realizable, adversarial 3D-printed object that misleads an AD system to fail in detecting it and thus crash into it. We propose a novel attack pipeline that addresses two main design challenges: (1) non-differentiable target camera and LiDAR sensing systems, and (2) non-differentiable cell-level aggregated features popularly used in LiDAR-based AD perception. We evaluate our attack on MSF included in representative open-source industry-grade AD systems in real-world driving scenarios. Our results show that the attack achieves over 90% success rate across different object types and MSF. Our attack is also found stealthy, robust to victim positions, transferable across MSF algorithms, and physical-world realizable after being 3D-printed and captured by LiDAR and camera devices. To concretely assess the end-to-end safety impact, we further perform simulation evaluation and show that it can cause a 100% vehicle collision rate for an industry-grade AD system.

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 20 code samples harvested from 1 repository linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 20 samples from 1 repository, 13 ran (13 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ASGuard-UCI/MSF-ADV mentioned on GitHubpytorchMITSyntology: 20 samples, 13 ran (0 instrument-failed) · 7 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

20 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 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.

13ran
7unverified

Licence: 0 of the 20 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 ASGuard-UCI/MSF-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. 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.

ASGuard-UCI/MSF-ADV community (archive-listed) 20 samples, 13 ran (0 instrument-failed) · 7 unverified
DJSFind cluster.py ran MIT (permissive) · 7ef997c38a692004 · report fixture: signature grid:list/1/DisjointSetElement, x:int/0/int · returned int · level recorded 2026-09-24
DJSFindRecursive cluster.py ran MIT (permissive) · 6758cb0e62752d1e · report fixture: signature grid:list/1/DisjointSetElement, x:int/0/int · returned int · level recorded 2026-09-24
get_ray render.py ran fingerprinted MIT (permissive) · c75aea10ccb39d17 · report fixture: signature x_final:Tensor/2/float, y_final:Tensor/2/float, z_final:Tensor/2/float · returned tuple · level recorded 2026-09-24
groupPc2Pixel c2p_segmentation.py ran MIT (permissive) · 96451f3f663c7855 · report fixture: signature PT:list/1/float, inv_res_x:float/0/float, range_:int/0/int · returned tuple · level recorded 2026-09-24
mapPointToGrid c2p_segmentation.py ran MIT (permissive) · 73745a40802ffe29 · report fixture: signature PCL:ndarray/2/float · returned list · level recorded 2026-09-24
my_ransac ground_detector_simple.py ran MIT (permissive) · 0a647dcbd2ecc065 · report fixture: signature data:ndarray/2/float, distance_threshold:float/0/float, P:float/0/float, sample_size:int/0/int, max_iterations:int/0/int, lidar_height:float/0/float, lidar_height_down:float/0/float, first_line_num:int/0/int, alpha_threshold:float/0/float, use_all_sample:bool/0/bool, y_limit:int/0/int · returned tuple · level recorded 2026-09-24
processPC inject_cube.py ran MIT (permissive) · 7a7d3e104a7ab70c · report fixture: signature PC:ndarray/2/float, min_h:int/0/int, max_h:int/0/int, min_v:int/0/int, max_v:int/0/int · returned tuple · level recorded 2026-09-24
rc2grid c2p_segmentation.py ran fingerprinted MIT (permissive) · f29ebe1a2f55300d · report fixture: signature r:int/0/int, c:int/0/int · returned int · level recorded 2026-09-24
read_cali attack.py ran MIT (permissive) · 560fface17f291b4 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-24
render in 19 papers render.py ran MIT (permissive) · 810e3276e34039fe · report fixture: signature ray_direction:Tensor/2/float, length:Tensor/1/float, vertex:Tensor/2/float, face:Tensor/2/int, i_final:Tensor/1/float · returned Tensor · level recorded 2026-09-24
render_div render.py ran MIT (permissive) · 99bee8a1ad6f406f · report fixture: signature ray_direction:Tensor/2/float, length:Tensor/1/float, vertex:Tensor/2/float, face:Tensor/2/int, i_final:Tensor/1/float · returned tuple · level recorded 2026-09-24
xyz2grid xyz2grid.py ran MIT (permissive) · 50f11d1830ea88b9 · report fixture: signature x_var:Tensor/2/float, y_var:Tensor/2/float, z_var:Tensor/2/float, X_RES:int/0/int, Y_RES:int/0/int, H_RES:int/0/int · returned Tensor · level recorded 2026-09-24
xyzi2gridhard xyz2grid.py ran MIT (permissive) · a59cf65f2fe6255f · report fixture: signature x_var:Tensor/2/float, y_var:Tensor/2/float, z_var:Tensor/2/float, i_var:Tensor/2/float, X_RES:int/0/int, Y_RES:int/0/int, H_RES:int/0/int · returned Tensor · level recorded 2026-09-24
estimate_plane ground_detector_simple.py unverified MIT (permissive) · 559aaaf2325a4e86 · report
injectCube inject_cube.py unverified MIT (permissive) · c9790fbf34397045 · report
injectCylinder inject_cube.py unverified MIT (permissive) · 4bc27814ce2c2d13 · report
lossRenderAttack loss_LiDAR.py unverified MIT (permissive) · 4eac161e796b8b53 · report
my_ransac_v3 ground_detector_simple.py unverified MIT (permissive) · f555463c4444b6aa · report
predict_convert attack.py unverified MIT (permissive) · db86dfb6ec8f0a09 · report
xyzi2grid_v2 xyz2grid.py unverified MIT (permissive) · 3c0901495eeeb97f · report

Tasks

Autonomous DrivingSensor Fusion

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