SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.08327 · 2020

Fawkes: Protecting Privacy against Unauthorized Deep Learning Models

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 (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-21; 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/2002.08327.json · badge: /api/ran/2002.08327.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
Shawn-Shan/fawkes canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
generate_cloak_images Ran
ran; our contract draft was wrong, not the code
Shawn-Shan/fawkes/fawkes/protection.py
code served (permissive licence) · get_code("32e7e2eb0126f79f")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch
import torch.nn as nn

torch.manual_seed(0)

class Protector(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def compute(self, image_X, target_emb=None):
        # Simple protector that applies a linear transformation
        # to simulate cloaking
        if target_emb is not None:
            return self.linear(image_X) + target_emb
        else:
            return self.linear(image_X)

protector = Protector()

# Batch size 2, image feature dimension 4
image_X = torch.randn(2, 4)

# Target embedding with different dimension (3) for distinctness
target_emb = torch.randn(2, 4)

ARGS = {
    "protector": protector,
    "image_X": image_X,
    "target_emb": target_emb,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 4) — shape (2, 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

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Today's proliferation of powerful facial recognition systems poses a real threat to personal privacy. As Clearview.ai demonstrated, anyone can canvas the Internet for data and train highly accurate facial recognition models of individuals without their knowledge. We need tools to protect ourselves from potential misuses of unauthorized facial recognition systems. Unfortunately, no practical or effective solutions exist. In this paper, we propose Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models. Fawkes achieves this by helping users add imperceptible pixel-level changes (we call them "cloaks") to their own photos before releasing them. When used to train facial recognition models, these "cloaked" images produce functional models that consistently cause normal images of the user to be misidentified. We experimentally demonstrate that Fawkes provides 95+% protection against user recognition regardless of how trackers train their models. Even when clean, uncloaked images are "leaked" to the tracker and used for training, Fawkes can still maintain an 80+% protection success rate. We achieve 100% success in experiments against today's state-of-the-art facial recognition services. Finally, we show that Fawkes is robust against a variety of countermeasures that try to detect or disrupt image cloaks.

For agents

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

get_harvested_code_for_paper("2002.08327")
get_code_for_paper("2002.08327")
have("2002.08327")

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

curl https://syntology.ai/api/ran/2002.08327.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.08327.svg)](https://syntology.ai/paper/2002.08327)

Connect an agent — have() is free.