SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.01823 · NeurIPS · 2021

Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations

Amit Roy-Chowdhury, Shasha Li, Abhishek Aich, Shitong Zhu, M Asif, Chengyu Song, Srikanth Krishnamurthy

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 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; 6 failures of our instrument; 3 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/2110.01823.json · badge: /api/ran/2110.01823.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
sli057/geo-trap canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
sli057/Geo-TRAP marked official in Papers with Code
Papers with Code archive
6 ran · 2 no recorded run
FunctionStatusWhere it lives
get_g_star Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("5b5842468546e94e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

norm2 Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("49c4e33835060f89")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

targeted_pert_loss Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("bbfe039161c891d2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

untargeted_cross_entropy_pert_loss Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("4579281f59cd36a0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

untargeted_cw2_pert_loss Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("7a37435bd064e574")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

untargeted_pert_loss Ran
ran; our contract draft was wrong, not the code
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("5d73ab5fc29a8067")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

code_p Not yet run
unverified (harvested, no recorded run)
sli057/geo-trap/query_attack/decompose_query.py
pointer only (licence: NONE) · get_code("47253cd580c32fc0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/geo-trap when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

perturbation_image Not yet run
unverified (harvested, no recorded run)
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("4b161e5260f69a8b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

wrap_with_optical_flow Not yet run
unverified (harvested, no recorded run)
sli057/Geo-TRAP/query_attack/query_frame_util.py
pointer only (licence: NONE) · get_code("3fdb72114246823e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sli057/Geo-TRAP when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

When compared to the image classification models, black-box adversarial attacks against video classification models have been largely understudied. This could be possible because, with video, the temporal dimension poses significant additional challenges in gradient estimation. Query-efficient black-box attacks rely on effectively estimated gradients towards maximizing the probability of misclassifying the target video. In this work, we demonstrate that such effective gradients can be searched for by parameterizing the temporal structure of the search space with geometric transformations. Specifically, we design a novel iterative algorithm Geometric TRAnsformed Perturbations (GEO-TRAP), for attacking video classification models. GEO-TRAP employs standard geometric transformation operations to reduce the search space for effective gradients into searching for a small group of parameters that define these operations. This group of parameters describes the geometric progression of gradients, resulting in a reduced and structured search space. Our algorithm inherently leads to successful perturbations with surprisingly few queries. For example, adversarial examples generated from GEO-TRAP have better attack success rates with ∼ 73.55% fewer queries compared to the state-of-the-art method for video adversarial attacks on the widely used Jester dataset. Overall, our algorithm exposes vulnerabilities of diverse video classification models and achieves new state-of-the-art results under black-box settings on two large datasets. Code is available here: https://github.com/sli057/Geo-TRAP

For agents

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

get_harvested_code_for_paper("2110.01823")
get_code_for_paper("2110.01823")
have("2110.01823")

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

curl https://syntology.ai/api/ran/2110.01823.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.01823.svg)](https://syntology.ai/paper/2110.01823)

Connect an agent — have() is free.