SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1802.06430 · 2018

DARTS: Deceiving Autonomous Cars with Toxic Signs

arXiv · PDF · Open in the Atlas

Code that ran

3 of 11 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 3 have no contract verdict; 0 failures of our instrument; 8 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/1802.06430.json · badge: /api/ran/1802.06430.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
inspire-group/advml-traffic-sign canonical (classifier label)
classifier basis: census
3 ran · 8 no recorded run
FunctionStatusWhere it lives
bb_iou Ran
ran on a synthesized input
inspire-group/advml-traffic-sign/lib/detector_utils.py
code served (permissive licence) · get_code("80ca270a177b2a57")
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, through the batch API) and returned float, ndim 0, dtype family float, shape () 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 torch

torch.manual_seed(0)

# The function bb_iou takes two bounding boxes represented as sequences with 4 elements each
# [x1, y1, x2, y2] where (x1, y1) is top-left and (x2, y2) is bottom-right

boxA = [10, 20, 50, 80]
boxB = [30, 40, 70, 100]

ARGS = {
    "boxA": boxA,
    "boxB": boxB
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
error_rate Ran
ran on a synthesized input
inspire-group/advml-traffic-sign/lib/tf_utils.py
code served (permissive licence) · get_code("8faa83f81cb4c3e6")
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, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type 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

# Create small sample predictions and labels
# predictions: shape (batch_size, num_classes) with soft predictions/logits
# labels: shape (batch_size, num_classes) with one-hot encoded labels

batch_size = 2
num_classes = 4

# Create predictions (soft predictions/logits)
predictions = np.random.randn(batch_size, num_classes).astype(np.float32)
# Make them somewhat reasonable by using softmax-like values
predictions = np.exp(predictions) / np.sum(np.exp(predictions), axis=1, keepdims=True)

# Create one-hot encoded labels
labels = np.zeros((batch_size, num_classes), dtype=np.float32)
labels[0, 1] = 1.0  # First sample belongs to class 1
labels[1, 3] = 1.0  # Second sample belongs to class 3

ARGS = {
    "predictions": predictions,
    "labels": labels,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
rgb2gray Ran
ran on a synthesized input
inspire-group/advml-traffic-sign/lib/utils.py
code served (permissive licence) · get_code("ed8e524e657c33b4")
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, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (4, 5) 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 torch
import numpy as np

torch.manual_seed(0)

# Create a 3D RGB image (height, width, channels)
image_3d = torch.rand(4, 5, 3)

# Create a 4D batch of RGB images (batch, height, width, channels)
image_4d = torch.rand(2, 4, 5, 3)

# Test with 3D image
ARGS = {
    "image": image_3d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (4, 5) — shape (4, 5) 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
fg Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/attacks.py
code served (permissive licence) · get_code("162c53ddcf7aa350")
How it ran

no invocation recorded.

find_circles Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/detector_utils.py
code served (permissive licence) · get_code("c5f93b102a16935d")
How it ran

no invocation recorded.

gradient_fn Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/keras_utils.py
code served (permissive licence) · get_code("4f29c71c0bd12657")
How it ran

no invocation recorded.

gradient_model Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/keras_utils.py
code served (permissive licence) · get_code("d4cc996eeea5bcc0")
How it ran

no invocation recorded.

iterative Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/attacks.py
code served (permissive licence) · get_code("74d9a97000951671")
How it ran

no invocation recorded.

output_fn Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/keras_utils.py
code served (permissive licence) · get_code("215dd352688c6d02")
How it ran

no invocation recorded.

read_bb Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/detector_utils.py
code served (permissive licence) · get_code("077c9725ee37bfa5")
How it ran

no invocation recorded.

read_image Not yet run
unverified (harvested, no recorded run)
inspire-group/advml-traffic-sign/lib/utils.py
code served (permissive licence) · get_code("f7c51343819bf34f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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 11 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

Sign recognition is an integral part of autonomous cars. Any misclassification of traffic signs can potentially lead to a multitude of disastrous consequences, ranging from a life-threatening accident to even a large-scale interruption of transportation services relying on autonomous cars. In this paper, we propose and examine security attacks against sign recognition systems for Deceiving Autonomous caRs with Toxic Signs (we call the proposed attacks DARTS). In particular, we introduce two novel methods to create these toxic signs. First, we propose Out-of-Distribution attacks, which expand the scope of adversarial examples by enabling the adversary to generate these starting from an arbitrary point in the image space compared to prior attacks which are restricted to existing training/test data (In-Distribution). Second, we present the Lenticular Printing attack, which relies on an optical phenomenon to deceive the traffic sign recognition system. We extensively evaluate the effectiveness of the proposed attacks in both virtual and real-world settings and consider both white-box and black-box threat models. Our results demonstrate that the proposed attacks are successful under both settings and threat models. We further show that Out-of-Distribution attacks can outperform In-Distribution attacks on classifiers defended using the adversarial training defense, exposing a new attack vector for these defenses.

For agents

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

get_harvested_code_for_paper("1802.06430")
get_code_for_paper("1802.06430")
have("1802.06430")

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

curl https://syntology.ai/api/ran/1802.06430.json

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

[![Syntology run record](https://syntology.ai/api/ran/1802.06430.svg)](https://syntology.ai/paper/1802.06430)

Connect an agent — have() is free.