SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.05810 · 2018

ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector

arXiv · PDF · Open in the Atlas

Code that ran

3 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1804.05810.json · badge: /api/ran/1804.05810.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
shangtse/robust-physical-attack canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
AishrithRao/robust-physical-attack community (classifier label)
classifier basis not recorded on the link
2 ran · 2 no recorded run
FunctionStatusWhere it lives
generate_data Ran
ran on a synthesized input
AishrithRao/robust-physical-attack/shapeshifter2d.py
pointer only (licence: BSD-3-Clause) · get_code("76947627228fb26a")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, AishrithRao/robust-physical-attack, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

generate_transforms Ran
ran on a synthesized input
AishrithRao/robust-physical-attack/shapeshifter2d.py
pointer only (licence: BSD-3-Clause) · get_code("c131cd2e286561d2")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, AishrithRao/robust-physical-attack, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_and_tile_images Ran
ran; our contract draft was wrong, not the code
shangtse/robust-physical-attack/shapeshifter.py
code served (permissive licence) · get_code("6153f3aa149b9b04")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned ndarray, ndim 4, dtype family float, shape (6, 8, 8, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from PIL import Image
import tempfile
import os

# Create temporary test images
temp_dir = tempfile.mkdtemp()

# Create a simple 10x10 RGB image and save it
img1 = Image.new('RGB', (10, 10), color=(255, 0, 0))
path1 = os.path.join(temp_dir, 'test1.png')
img1.save(path1)

# Create another simple 10x10 RGB image and save it
img2 = Image.new('RGB', (10, 10), color=(0, 255, 0))
path2 = os.path.join(temp_dir, 'test2.png')
img2.save(path2)

ARGS = {
    'paths': [path1, path2],
    'replicates': 2,
    'resize': (8, 8)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 4, dtype family float, shape (6, 8, 8, 3) — shape (6, 8, 8, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_composited_images Not yet run
unverified (harvested, no recorded run)
AishrithRao/robust-physical-attack/shapeshifter2d.py
pointer only (licence: BSD-3-Clause) · get_code("2f1c2d887aa2b89d")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, AishrithRao/robust-physical-attack, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

create_textures Not yet run
unverified (harvested, no recorded run)
AishrithRao/robust-physical-attack/shapeshifter.py
pointer only (licence: BSD-3-Clause) · get_code("273b94046679261e")
How it ran

The body of this sample is withheld: BSD-3-Clause, as GitHub detects it on this paper's repository, AishrithRao/robust-physical-attack, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work. In this work, we propose ShapeShifter, an attack that tackles the more challenging problem of crafting physical adversarial perturbations to fool image-based object detectors like Faster R-CNN. Attacking an object detector is more difficult than attacking an image classifier, as it needs to mislead the classification results in multiple bounding boxes with different scales. Extending the digital attack to the physical world adds another layer of difficulty, because it requires the perturbation to be robust enough to survive real-world distortions due to different viewing distances and angles, lighting conditions, and camera limitations. We show that the Expectation over Transformation technique, which was originally proposed to enhance the robustness of adversarial perturbations in image classification, can be successfully adapted to the object detection setting. ShapeShifter can generate adversarially perturbed stop signs that are consistently mis-detected by Faster R-CNN as other objects, posing a potential threat to autonomous vehicles and other safety-critical computer vision systems.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1804.05810")
get_code_for_paper("1804.05810")
have("1804.05810")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1804.05810.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1804.05810.svg)](https://syntology.ai/paper/1804.05810)

Connect an agent — have() is free.