SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.09962 · CVPR · 2023

Adversarial Counterfactual Visual Explanations

Guillaume Jeanneret, Loïc Simon, Frédéric Jurie

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 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/2303.09962.json · badge: /api/ran/2303.09962.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
guillaumejs2403/ace marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Attack Ran
ran on a synthesized input · constructed an object; no result was computed
guillaumejs2403/ace/core/attacks_and_models.py
code served (permissive licence) · get_code("8861e9868b41a83f")
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 an instance of its own class, Attack: the run constructed the object and did not call it, so no result was computed. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Build a simple classifier model
class SimpleClassifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc = nn.Linear(4, 3)  # 4 input features, 3 classes
    
    def forward(self, x):
        # x shape: (batch, channels, height, width) or (batch, features)
        if x.dim() == 4:
            x = x.view(x.size(0), -1)  # flatten spatial dims
        return self.fc(x)

# Build a loss function
loss_fn = nn.CrossEntropyLoss()

# Build a distance function (e.g., L2 distance)
def dist_fn(x, x_adv):
    return torch.norm(x - x_adv, p=2)

# Create predictor (classifier)
predict = SimpleClassifier()

# Define attack parameters
eps = 0.3
step = 1 / 255
nb_iter = 10
norm = 'linf'
dist_schedule = 'none'
binary = False

ARGS = {
    'predict': predict,
    'loss_fn': loss_fn,
    'dist_fn': dist_fn,
    'eps': eps,
    'step': step,
    'nb_iter': nb_iter,
    'norm': norm,
    'dist_schedule': dist_schedule,
    'binary': binary
}
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 Attack — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Attack output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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

Counterfactual explanations and adversarial attacks have a related goal: flipping output labels with minimal perturbations regardless of their characteristics. Yet, adversarial attacks cannot be used directly in a counterfactual explanation perspective, as such perturbations are perceived as noise and not as actionable and understandable image modifications. Building on the robust learning literature, this paper proposes an elegant method to turn adversarial attacks into semantically meaningful perturbations, without modifying the classifiers to explain. The proposed approach hypothesizes that Denoising Diffusion Probabilistic Models are excellent regularizers for avoiding highfrequency and out-of-distribution perturbations when generating adversarial attacks. The paper's key idea is to build attacks through a diffusion model to polish them. This allows studying the target model regardless of its robustification level. Extensive experimentation shows the advantages of our counterfactual explanation approach over current State-of-the-Art in multiple testbeds.

For agents

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

get_harvested_code_for_paper("2303.09962")
get_code_for_paper("2303.09962")
have("2303.09962")

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

curl https://syntology.ai/api/ran/2303.09962.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.09962.svg)](https://syntology.ai/paper/2303.09962)

Connect an agent — have() is free.