Papers › Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces
Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces
Fahad Shamshad, Koushik Srivatsan, Karthik Nandakumar
The ability of generative models to produce highly realistic synthetic face images has raised security and ethical concerns. As a first line of defense against such fake faces, deep learning based forensic classifiers have been developed. While these forensic models can detect whether a face image is synthetic or real with high accuracy, they are also vulnerable to adversarial attacks. Although such attacks can be highly successful in evading detection by forensic classifiers, they introduce visible noise patterns that are detectable through careful human scrutiny. Additionally, these attacks assume access to the target model(s) which may not always be true. Attempts have been made to directly perturb the latent space of GANs to produce adversarial fake faces that can circumvent forensic classifiers. In this work, we go one step further and show that it is possible to successfully generate adversarial fake faces with a specified set of attributes (e.g., hair color, eye size, race, gender, etc.). To achieve this goal, we leverage the state-of-the-art generative model StyleGAN with disentangled representations, which enables a range of modifications without leaving the manifold of natural images. We propose a framework to search for adversarial latent codes within the feature space of StyleGAN, where the search can be guided either by a text prompt or a reference image. We also propose a meta-learning based optimization strategy to achieve transferable performance on unknown target models. Extensive experiments demonstrate that the proposed approach can produce semantically manipulated adversarial fake faces, which are true to the specified attribute set and can successfully fool forensic face classifiers, while remaining undetectable by humans. Code: https://github.com/koushiksrivats/face_attribute_attack.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2306.13091")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2306.13091", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2306.13091")
Code
Syntology 20 code samples harvested from 1 repository linked to this paper: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 20 samples from 1 repository, 12 ran (9 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
20 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 20 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from koushiksrivats/face_attribute_attack. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
6a657c5a423ebb1b · report
fixture: returned Blur · level recorded 2026-09-22 6ac39cc25c802292 · report
fixture: returned ConstantInput · level recorded 2026-09-22 e47588046427d5bf · report
fixture: returned EqualLinear · level recorded 2026-09-22 49d075452b1d32c2 · report
fixture: returned FusedLeakyReLU · level recorded 2026-09-22 1ec76c108312391c · report
fixture: returned Generator · level recorded 2026-09-22 a14989f041846d5f · report
fixture: signature resize:int/0/int · returned Compose · level recorded 2026-09-22 6a89165f91afae45 · report
fixture: signature image:Tensor/4/float, noise:NoneType/0/? · returned Tensor · level recorded 2026-09-22 3aff569b0f560591 · report
fixture: returned Normalize · level recorded 2026-09-22 9b4774177e343e0b · report
fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-22 9a98641c4a409588 · report
fixture: returned Upsample · level recorded 2026-09-22 238fedc043c13f62 · report
fixture: signature input:Tensor/4/float, kernel:Tensor/2/float, up:int/0/int, down:int/0/int, pad:tuple/1/int · returned Tensor · level recorded 2026-09-22 census: 5 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 image_as_reference.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only ·
fe99cfd294676edb · report
fixture: signature input:Tensor/4/float, kernel:Tensor/2/float, up_x:int/0/int, up_y:int/0/int, down_x:int/0/int, down_y:int/0/int, pad_x0:int/0/int, pad_x1:int/0/int, pad_y0:int/0/int, pad_y1:int/0/int · returned Tensor · level recorded 2026-09-22 673fcfe5abee6fa2 · report
dabdb31d4bd12319 · report
995aad99045f4c4d · report
223870c61558817c · report
737ec98d1a59d066 · report
dd91635c995516a5 · report
cc2b94960ff33e11 · report
0910a44fbe46f84f · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for Attribute-Conditioned Adversarial Faces (graph method: Attribute-Conditioned Adversarial Faces). 21 bricks; individually on a fixture: 13 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.
- image_as_reference entry · level 0 · unverified ·
0910a44fbe46f84f - ImageTransform data_transform · level 1 · ran · our draft was wrong ·
a14989f041846d5f - get_classifier model · level 0 · unverified ·
dd91635c995516a5 - get_stylegan_generator model · level 0 · unverified ·
cc2b94960ff33e11 - Normalize helper · level 1 · ran ·
3aff569b0f560591 - Generator helper · level 1 · ran ·
1ec76c108312391c - ensure_checkpoint_exists helper · level 0 · unverified ·
223870c61558817c - ConstantInput helper · level 1 · ran ·
6ac39cc25c802292 - EqualLinear helper · level 1 · ran ·
e47588046427d5bf - PixelNorm helper · level 1 · ran ·
9b4774177e343e0b - StyledConv helper · level 0 · unverified ·
dabdb31d4bd12319 - ToRGB helper · level 0 · unverified ·
995aad99045f4c4d - fused_leaky_relu helper · level 0 · unverified ·
737ec98d1a59d066 - FusedLeakyReLU helper · level 1 · ran ·
49d075452b1d32c2 - ModulatedConv2d helper · level 0 · unverified ·
673fcfe5abee6fa2 - NoiseInjection helper · level 1 · ran ·
6a89165f91afae45 - Upsample helper · level 1 · ran ·
9a98641c4a409588 - Blur helper · level 1 · ran ·
6a657c5a423ebb1b - make_kernel helper · level 1 · ran · violated contract ·
6f65e378a4313f87 - upfirdn2d helper · level 1 · ran; the contract check could not run (RAISES) ·
238fedc043c13f62 - upfirdn2d_native helper · level 1 · ran; the contract check could not run (RAISES) ·
fe99cfd294676edb
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2306.13091") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections