SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.18864 · 2024

Privacy-Preserving Autoencoder for Collaborative Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 0 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/2402.18864.json · badge: /api/ran/2402.18864.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
bardia-az/ppa-code canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
autopad Ran
ran, honoured the contract we drafted
bardia-az/ppa-code/models/common.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from yang-0201/YOLOv6_pro, is pointer only (licence: GPL-3.0) · get_code("988a3c854b1b13d0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from yang-0201/YOLOv6_pro, and GPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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.

get_tensors Ran
ran; our contract draft was wrong, not the code
bardia-az/ppa-code/compress.py
code served (permissive licence) · get_code("8c6f03cc2cad8cde")
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 (2, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build a minimal model that accepts img and cut_model parameter
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 5)
    
    def forward(self, img, cut_model=None):
        # The function calls model(img, cut_model=1)
        # Just apply linear transformation
        return self.linear(img)

# Build a minimal autoencoder that has enc task
class SimpleAutoencoder(nn.Module):
    def __init__(self):
        super().__init__()
        self.enc_layer = nn.Linear(5, 3)
        self.dec_layer = nn.Linear(3, 5)
    
    def forward(self, x, task='enc'):
        # The function calls autoencoder(T, task='enc')
        if task == 'enc':
            return self.enc_layer(x)
        else:
            return self.dec_layer(x)

# Create instances
img = torch.randn(2, 4)  # batch size 2, 4 features
model = SimpleModel()
autoencoder = SimpleAutoencoder()

ARGS = {
    'img': img,
    'model': model,
    'autoencoder': autoencoder
}
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 Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 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
gradient_img Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bardia-az/ppa-code/utils/loss.py
code served (permissive licence) · get_code("3e02ccee31400bcb")
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. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create a small image tensor: batch_size=2, channels=3, height=4, width=4
img = torch.randn(2, 3, 4, 4, dtype=torch.float32)

ARGS = {
    "img": img
}
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 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
img_gradient_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bardia-az/ppa-code/utils/loss.py
code served (permissive licence) · get_code("78353360cd6d5870")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type and ndim 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 torch.nn as nn
import numpy as np

torch.manual_seed(0)

# Create small sample tensors with distinct dimensions
# pred and gt should be RGB images (batch, channels=3, height, width)
batch_size = 2
channels = 3
height = 4
width = 5

pred = torch.randn(batch_size, channels, height, width, dtype=torch.float32)
gt = torch.randn(batch_size, channels, height, width, dtype=torch.float32)

# MAX is a scalar representing the maximum pixel value (commonly 255 or 1.0)
MAX = 255.0

ARGS = {
    "pred": pred,
    "gt": gt,
    "MAX": MAX
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
read_y_channel Ran
ran, honoured the contract we drafted
bardia-az/ppa-code/compress.py
code served (permissive licence) · get_code("acc1e6db920b392c")
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 ndarray, ndim 2, dtype family int, shape (3, 4) 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 io
import numpy as np

# Create a mock file object with binary data
# We need w * h bytes for the raw image data
w = 4
h = 3
# Create random uint8 data
image_data = np.random.randint(0, 256, size=(h, w), dtype=np.uint8)
raw_bytes = image_data.tobytes()

# Create a BytesIO object to simulate a file
file = io.BytesIO(raw_bytes)

ARGS = {
    "file": file,
    "w": w,
    "h": h
}
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 ndarray, ndim 2, dtype family int, shape (3, 4) — shape (3, 4) 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
smooth_BCE Ran
ran, honoured the contract we drafted
bardia-az/ppa-code/utils/loss.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Gandolfczjh/APDE, is pointer only (licence: NONE) · get_code("386a04c4b6c96c88")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Gandolfczjh/APDE, and GitHub detected no licence in that repository when it was checked. 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.

tensors_to_tiled Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
bardia-az/ppa-code/compress.py
code served (permissive licence) · get_code("04c6ae7273f6d688")
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 (12, 6) 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)

# Create a tensor with shape (batch=1, channels=chs_in_w*chs_in_h, height=4, width=3)
# chs_in_w=2, chs_in_h=3, so channels = 2*3 = 6
chs_in_w = 2
chs_in_h = 3
tensor = torch.randn(1, chs_in_w * chs_in_h, 4, 3)

tensors_min = -1.0
tensors_max = 1.0

ARGS = {
    "tensor": tensor,
    "chs_in_w": chs_in_w,
    "chs_in_h": chs_in_h,
    "tensors_min": tensors_min,
    "tensors_max": tensors_max,
}
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 Tensor, ndim 2, dtype family float, shape (12, 6) — shape (12, 6) 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

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 1 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
autopad 23 other papers
16 dated earlier, 6 later, 1 same year, order not determinable · 1 only as an assembly brick
1311.2524 (2013-11)
Rich feature hierarchies for accurate object detection and semantic segmentation
1703.07402 (2017-03)
Simple Online and Realtime Tracking with a Deep Association Metric
1804.02767 (2018-04)
YOLOv3: An Incremental Improvement
and 20 more not named here
smooth_BCE 16 other papers
8 dated earlier, 1 the same month, 6 later, 1 same year, order not determinable
1611.02644 (2016-11)
Multispectral Deep Neural Networks for Pedestrian Detection
2108.11250 (2021-08)
YOLOP: You Only Look Once for Panoptic Driving Perception
2202.01811 (2022-02)
ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking
and 13 more not named here

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

Privacy is a crucial concern in collaborative machine vision where a part of a Deep Neural network (DNN) model runs on the edge, and the rest is executed on the cloud. In such applications, the machine vision model does not need the exact visual content to perform its task. Taking advantage of this potential, private information could be removed from the data insofar as it does not significantly impair the accuracy of the machine vision system. In this paper, we present an autoencoder-style network integrated within an object detection pipeline, which generates a latent representation of the input image that preserves task-relevant information while removing private information. Our approach employs an adversarial training strategy that not only removes private information from the bottleneck of the autoencoder but also promotes improved compression efficiency for feature channels coded by conventional codecs like VVC-Intra. We assess the proposed system using a realistic evaluation framework for privacy, directly measuring face and license plate recognition accuracy. Experimental results show that our proposed method is able to reduce the bitrate significantly at the same object detection accuracy compared to coding the input images directly, while keeping the face and license plate recognition accuracy on the images recovered from the bottleneck features low, implying strong privacy protection. Our code is available at https://github.com/bardia-az/ppa-code.

For agents

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

get_harvested_code_for_paper("2402.18864")
get_code_for_paper("2402.18864")
have("2402.18864")

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

curl https://syntology.ai/api/ran/2402.18864.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.18864.svg)](https://syntology.ai/paper/2402.18864)

Connect an agent — have() is free.