Papers › Manipulating Feature Visualizations with Gradient Slingshots

Manipulating Feature Visualizations with Gradient Slingshots

11 Jan 2024arXiv:2401.06122archive 2025-07-28

Dilyara Bareeva, Marina M. -C. Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck, Kirill Bykov

Deep Neural Networks (DNNs) are capable of learning complex and versatile representations, however, the semantic nature of the learned concepts remains unknown. A common method used to explain the concepts learned by DNNs is Feature Visualization (FV), which generates a synthetic input signal that maximally activates a particular neuron in the network. In this paper, we investigate the vulnerability of this approach to adversarial model manipulations and introduce a novel method for manipulating FV without significantly impacting the model's decision-making process. The key distinction of our proposed approach is that it does not alter the model architecture. We evaluate the effectiveness of our method on several neural network models and demonstrate its capabilities to hide the functionality of arbitrarily chosen neurons by masking the original explanations of neurons with chosen target explanations during model auditing.

PaperPDFCodeCode Syntology ran

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):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 12 ran (7 with no instrument failure; 5 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dilyabareeva/grad-slingshot officialmentioned in papermentioned on GitHubpytorchMITSyntology: 18 samples, 12 ran (5 instrument-failed) · 6 unverified report

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

18 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
7ran
6unverified

Licence: 0 of the 18 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 dilyabareeva/grad-slingshot. “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”. “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.

dilyabareeva/grad-slingshot official repository 18 samples, 12 ran (5 instrument-failed) · 6 unverified
act_max_top_k_from_dataset plotting.py ran MIT (permissive) · fdbaf0d0cb186b10 · report fixture: signature indices:list/1/int, denormalize:callable/0/?, dataset:MockDataset/0/?, random_sampling:bool/0/bool, k:int/0/int · returned tuple · level recorded 2026-09-24
activation_max_top_k plotting.py ran MIT (permissive) · 6dddfa6475cdc440 · report fixture: signature act_before:ndarray/1/float, denormalize:callable/0/?, images:ndarray/4/float, highlight_index:int/0/int, title:str/0/str · returned Figure · level recorded 2026-09-24
get_nested_attr in 5 papers core/forward_hook.py ran · our draft was wrong MIT (permissive) · cb99d67a4a505067 · report fixture: signature obj:callable/0/?, attr:str/0/str · returned str · level recorded 2026-09-24
imagenet_dream core/fv_transforms.py ran · our draft was wrong MIT (permissive) · 31aae0b81729befe · report fixture: signature out_dim:int/0/int · returned list · level recorded 2026-09-24
load_image_net_data data_loader.py ran MIT (permissive) · 610e532eeeafa90c · report fixture: signature path:str/0/str, subset:NoneType/0/?, add_subset:NoneType/0/?, pc:float/0/float, add_pc:float/0/float, extra_folders:NoneType/0/?, test_transforms:NoneType/0/? · returned tuple · level recorded 2026-09-24
make_layers in 155 papers models.py ran · our draft was wrong MIT (permissive) · b834e29a85d15c71 · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
one_d_collate_fn core/manipulation_set.py ran · our draft was wrong MIT (permissive) · d5da8ca746a0cf9b · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-24
preservation_loss core/loss.py ran MIT (permissive) · 3e2ee5b40f872f43 · report fixture: signature inputs:Tensor/2/float, model:callable/0/?, default_model:callable/0/?, default_hook:Hook/0/?, hook:Hook/0/?, target_act_fn:callable/0/?, man_indices_oh:Tensor/1/float, layer_str:str/0/str, default_layer_str:str/0/str, w:float/0/float · returned Tensor · level recorded 2026-09-24
preservation_loss_prox_pulse_ce core/loss.py ran MIT (permissive) · 3ae37e854aa2fc88 · report fixture: signature inputs:Tensor/2/float, model:callable/0/?, default_model:callable/0/?, default_hook:callable/0/?, hook:callable/0/?, target_act_fn:callable/0/?, man_indices_oh:Tensor/2/float, layer_str:str/0/str, default_layer_str:str/0/str, w:float/0/float · returned Tensor · level recorded 2026-09-24
read_target_image core/utils.py ran MIT (permissive) · 86aefbf00edf3f75 · report fixture: signature device:str/0/str, n_channels:int/0/int, target_path:str/0/str, normalize:callable/0/? · returned tuple · level recorded 2026-09-24
resize_transform core/fv_transforms.py ran · our draft was wrong MIT (permissive) · bdbfcdaff4df9f8e · report fixture: signature im_dim:int/0/int · returned Compose · level recorded 2026-09-24
vit_cls_token_target_direction core/target_activations.py ran MIT (permissive) · 60f19087598c4668 · report fixture: signature probe_path:str/0/str, device:str/0/str · returned function · level recorded 2026-09-24
fcfgs models.py unverified MIT (permissive) · 95db6492f04d7140 · report
load_cifar_data data_loader.py unverified MIT (permissive) · 20528158cd3429d4 · report
load_mnist_data in 8 papers data_loader.py unverified MIT (permissive) · f0c45d4ecbd11674 · report
manipulation_loss_grad_based core/loss.py unverified MIT (permissive) · d37c77213d240c9c · report
modified_vgg models.py unverified MIT (permissive) · 1ba3884299b9ff1c · report
vit_transforms core/fv_transforms.py unverified MIT (permissive) · 6e281e5c8b321a96 · report

Tasks

Decision Making

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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