SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.08449 · ICML · 2022

Adversarial Attacks on Gaussian Process Bandits

Jonathan Scarlett, Eric Han

arXiv · PDF · Open in the Atlas

Code that ran

1 of 6 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; 5 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/2110.08449.json · badge: /api/ran/2110.08449.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
eric-vader/attack-bo canonical (classifier label)
classifier basis not recorded on the link
1 ran · 5 no recorded run
FunctionStatusWhere it lives
singleton Ran
ran on a synthesized input
eric-vader/attack-bo/attack_bo/config.py
code served (permissive licence) · get_code("d56231e6344169be")
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, through the batch API) and returned function. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create a simple test class to use as a singleton
class SimpleService:
    def __init__(self):
        self.value = 42
        self.data = "initialized"

# The singleton function takes a single parameter: cls (a class)
ARGS = {
    "cls": SimpleService
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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: none by the harness; any seed is in the setup block
make_thing Not yet run
unverified (harvested, no recorded run)
eric-vader/attack-bo/attack_bo/robot_pushing/push_world.py
code served (permissive licence) · get_code("24a33a6a2a77b573")
How it ran

no invocation recorded.

robot_push_3d Not yet run
unverified (harvested, no recorded run)
eric-vader/attack-bo/attack_bo/robot_pushing/generate_simudata3.py
code served (permissive licence) · get_code("e0a1687c1fe753ed")
How it ran

no invocation recorded.

robot_push_4d Not yet run
unverified (harvested, no recorded run)
eric-vader/attack-bo/attack_bo/robot_pushing/generate_simudata4.py
code served (permissive licence) · get_code("60cc37d9729f7a74")
How it ran

no invocation recorded.

simu_push Not yet run
unverified (harvested, no recorded run)
eric-vader/attack-bo/attack_bo/robot_pushing/push_world.py
code served (permissive licence) · get_code("1ca648944822dc19")
How it ran

no invocation recorded.

simu_push2 Not yet run
unverified (harvested, no recorded run)
eric-vader/attack-bo/attack_bo/robot_pushing/push_world.py
code served (permissive licence) · get_code("79b71e0e84906053")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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

Gaussian processes (GP) are a widely-adopted tool used to sequentially optimize black-box functions, where evaluations are costly and potentially noisy. Recent works on GP bandits have proposed to move beyond random noise and devise algorithms robust to adversarial attacks. This paper studies this problem from the attacker's perspective, proposing various adversarial attack methods with differing assumptions on the attacker's strength and prior information. Our goal is to understand adversarial attacks on GP bandits from theoretical and practical perspectives. We focus primarily on targeted attacks on the popular GP-UCB algorithm and a related elimination-based algorithm, based on adversarially perturbing the function f to produce another function f whose optima are in some target region R target . Based on our theoretical analysis, we devise both white-box attacks (known f ) and black-box attacks (unknown f ), with the former including a Subtraction attack and Clipping attack, and the latter including an Aggressive subtraction attack. We demonstrate that adversarial attacks on GP bandits can succeed in forcing the algorithm towards R target even with a low attack budget, and we test our attacks' effectiveness on a diverse range of objective functions.

For agents

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

get_harvested_code_for_paper("2110.08449")
get_code_for_paper("2110.08449")
have("2110.08449")

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

curl https://syntology.ai/api/ran/2110.08449.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.08449.svg)](https://syntology.ai/paper/2110.08449)

Connect an agent — have() is free.