SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.02014 · ICLR · 2022

Online Adversarial Attacks

Joey Avishek, Bose, Gauthier Gidel, Hugo Berard, Pascal Vincent, Simon Lacoste-Julien, William Hamilton, Andjela Mladenovic

arXiv · PDF · Open in the Atlas

Code that ran

1 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/2103.02014.json · badge: /api/ran/2103.02014.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
facebookresearch/OnlineAttacks marked official in Papers with Code
Papers with Code archive
1 ran · 2 no recorded run
FunctionStatusWhere it lives
StochasticVirtual Ran
ran on a synthesized input
facebookresearch/OnlineAttacks/online_attacks/online_algorithms/stochastic_virtual.py
code served (permissive licence) · get_code("a662e513f06cc1bc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned NoneType. 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 numpy as np

# INIT_ARGS for StochasticVirtual.__init__
INIT_ARGS = {
    'N': 100,
    'k': 5,
    'threshold': 38,
    'exhaust': True
}

# ARGS for StochasticVirtual.action
ARGS = {
    'value': 0.75,
    'index': 10
}

# METHOD specifies which method to call
METHOD = 'action'
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type NoneType — a NoneType output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NoneType 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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
Algorithm Not yet run
unverified (harvested, no recorded run)
facebookresearch/OnlineAttacks/online_attacks/online_algorithms/stochastic_virtual.py
code served (permissive licence) · get_code("99fa9075f7f15617")
How it ran

no invocation recorded.

AlgorithmType Not yet run
unverified (harvested, no recorded run)
facebookresearch/OnlineAttacks/online_attacks/online_algorithms/stochastic_virtual.py
code served (permissive licence) · get_code("19c4dea4362aedb9")
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

Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream. In this paper, we formalize the online adversarial attack problem, emphasizing two key elements found in real-world use-cases: attackers must operate under partial knowledge of the target model, and the decisions made by the attacker are irrevocable since they operate on a transient data stream. We first rigorously analyze a deterministic variant of the online threat model by drawing parallels to the well-studied ksecretary problem in theoretical computer science and propose VIRTUAL+, a simple yet practical online algorithm. Our main theoretical result shows VIRTUAL+ yields provably the best competitive ratio over all single-threshold algorithms for k < 5-extending the previous analysis of the k-secretary problem. We also introduce the stochastic k-secretary-effectively reducing online blackbox transfer attacks to a k-secretary problem under noise-and prove theoretical bounds on the performance of VIRTUAL+ adapted to this setting. Finally, we complement our theoretical results by conducting experiments on MNIST, CIFAR-10, and Imagenet classifiers, revealing the necessity of online algorithms in achieving near-optimal performance and also the rich interplay between attack strategies and online attack selection, enabling simple strategies like FGSM to outperform stronger adversaries.

For agents

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

get_harvested_code_for_paper("2103.02014")
get_code_for_paper("2103.02014")
have("2103.02014")

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

curl https://syntology.ai/api/ran/2103.02014.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.02014.svg)](https://syntology.ai/paper/2103.02014)

Connect an agent — have() is free.