SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.12588 · ICML · 2024

Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks

Jesse Cresswell, George Stein, Adam Dziedzic, Jiapeng Wu, Atiyeh Ghomi, Franziska Boenisch, Yi Sui, Antoni Kowalczuk, Jan Dubi

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2407.12588.json · badge: /api/ran/2407.12588.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
layer6ai-labs/ssl-robustness canonical (classifier label)
classifier basis: census
2 ran · 1 no recorded run
FunctionStatusWhere it lives
evaluate_accuracy Ran
ran, honoured the contract we drafted
layer6ai-labs/ssl-robustness/evaluators/evaluate.py
code served (permissive licence) · get_code("558456af4ed51313")
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
import torch.nn as nn

torch.manual_seed(0)

# Define a minimal classifier that satisfies the function's usage
class Classifier(nn.Module):
    def __init__(self):
        super().__init__()
        self.clf = nn.Linear(4, 3)  # Input dim 4, output dim 3 (3 classes)
    
    def forward(self, x):
        return self.clf(x)

# Create classifier instance
classifier = Classifier()

# Create a simple data loader (list of batches with inputs and labels)
# Each batch is a tuple of (inputs, labels)
loader = [
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
    (torch.randn(2, 4), torch.randint(0, 3, (2,))),
]

# Set device to CPU
device = torch.device('cpu')

ARGS = {
    'classifier': classifier,
    'loader': loader,
    'device': device,
}
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
modify_state_dict_naming Ran
ran; our contract draft was wrong, not the code
layer6ai-labs/ssl-robustness/models/ssl_models/utils.py
code served (permissive licence) · get_code("ef9a03512c2c7a95")
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 dict. 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)

# Create two state dicts with matching tensor shapes
# The function iterates through current_model_kvpair and matches with pretrained_model_kvpair
# It checks for 'fc' in names and asserts shape equality

current_model_kvpair = {
    'layer1.weight': torch.randn(4, 3),
    'layer1.bias': torch.randn(4),
    'layer2.weight': torch.randn(5, 4),
    'layer2.bias': torch.randn(5),
    'fc.weight': torch.randn(2, 5),
    'fc.bias': torch.randn(2),
}

pretrained_model_kvpair = {
    'conv1.weight': torch.randn(4, 3),
    'conv1.bias': torch.randn(4),
    'conv2.weight': torch.randn(5, 4),
    'conv2.bias': torch.randn(5),
    'dense.weight': torch.randn(2, 5),
    'dense.bias': torch.randn(2),
}

ARGS = {
    'current_model_kvpair': current_model_kvpair,
    'pretrained_model_kvpair': pretrained_model_kvpair,
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
load_weights_from_ckpt Not yet run
unverified (harvested, no recorded run)
layer6ai-labs/ssl-robustness/models/ssl_models/utils.py
code served (permissive licence) · get_code("f09930a7f42f6ff1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Large-scale vision models have become integral in many applications due to their unprecedented performance and versatility across downstream tasks. However, the robustness of these foundation models has primarily been explored for a single task, namely image classification. The vulnerability of other common vision tasks, such as semantic segmentation and depth estimation, remains largely unknown. We present a comprehensive empirical evaluation of the adversarial robustness of self-supervised vision encoders across multiple downstream tasks. Our attacks operate in the encoder embedding space and at the downstream task output level. In both cases, current state-of-the-art adversarial fine-tuning techniques tested only for classification significantly degrade clean and robust performance on other tasks. Since the purpose of a foundation model is to cater to multiple applications at once, our findings reveal the need to enhance encoder robustness more broadly. Our code is available at github.com/layer6ai-labs/ssl-robustness.

For agents

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

get_harvested_code_for_paper("2407.12588")
get_code_for_paper("2407.12588")
have("2407.12588")

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

curl https://syntology.ai/api/ran/2407.12588.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.12588.svg)](https://syntology.ai/paper/2407.12588)

Connect an agent — have() is free.