SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.01873 · 2024

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 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/2406.01873.json · badge: /api/ran/2406.01873.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
UCF-ML-Research/CR-UTP canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
gather_2d_on_last_dim Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
UCF-ML-Research/CR-UTP/Trigger/rlprompt/losses/loss_utils.py
pointer only (licence: NONE) · get_code("b812784740a81e0d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UCF-ML-Research/CR-UTP 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.

get_reward_shaping_func Ran
ran; our contract draft was wrong, not the code
UCF-ML-Research/CR-UTP/Trigger/rlprompt/modules/module_utils.py
pointer only (licence: NONE) · get_code("47741c361be09146")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UCF-ML-Research/CR-UTP 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.

get_masked_mean_min_max Not yet run
unverified (harvested, no recorded run)
UCF-ML-Research/CR-UTP/Trigger/rlprompt/losses/loss_utils.py
pointer only (licence: NONE) · get_code("4d8f96f19e31bf03")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UCF-ML-Research/CR-UTP 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.

masked_reverse_cumsum Not yet run
unverified (harvested, no recorded run)
UCF-ML-Research/CR-UTP/Trigger/rlprompt/losses/loss_utils.py
pointer only (licence: NONE) · get_code("7e5f5859a590dce8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, UCF-ML-Research/CR-UTP 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 1 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.

FunctionAlso present inEarliest-datedOthers named
gather_2d_on_last_dim 1 other paper
1 dated earlier
2306.06815 (2023-06)
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
get_masked_mean_min_max 1 other paper
1 dated earlier
2306.06815 (2023-06)
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
masked_reverse_cumsum 1 other paper
1 dated earlier
2306.06815 (2023-06)
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

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

It is imperative to ensure the stability of every prediction made by a language model; that is, a language's prediction should remain consistent despite minor input variations, like word substitutions. In this paper, we investigate the problem of certifying a language model's robustness against Universal Text Perturbations (UTPs), which have been widely used in universal adversarial attacks and backdoor attacks. Existing certified robustness based on random smoothing has shown considerable promise in certifying the input-specific text perturbations (ISTPs), operating under the assumption that any random alteration of a sample's clean or adversarial words would negate the impact of sample-wise perturbations. However, with UTPs, masking only the adversarial words can eliminate the attack. A naive method is to simply increase the masking ratio and the likelihood of masking attack tokens, but it leads to a significant reduction in both certified accuracy and the certified radius due to input corruption by extensive masking. To solve this challenge, we introduce a novel approach, the superior prompt search method, designed to identify a superior prompt that maintains higher certified accuracy under extensive masking. Additionally, we theoretically motivate why ensembles are a particularly suitable choice as base prompts for random smoothing. The method is denoted by superior prompt ensembling technique. We also empirically confirm this technique, obtaining state-of-the-art results in multiple settings. These methodologies, for the first time, enable high certified accuracy against both UTPs and ISTPs. The source code of CR-UTP is available at \url {https://github.com/UCFML-Research/CR-UTP}.

For agents

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

get_harvested_code_for_paper("2406.01873")
get_code_for_paper("2406.01873")
have("2406.01873")

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

curl https://syntology.ai/api/ran/2406.01873.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.01873.svg)](https://syntology.ai/paper/2406.01873)

Connect an agent — have() is free.