SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.15570 · 2024

Fast Adversarial Attacks on Language Models In One GPU Minute

arXiv · PDF · Open in the Atlas

Code that ran

3 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; 3 failures of our instrument; 1 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/2402.15570.json · badge: /api/ran/2402.15570.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
vinusankars/beast canonical (classifier label)
classifier basis: census
3 ran · 1 no recorded run
FunctionStatusWhere it lives
get_file Ran
ran; our contract draft was wrong, not the code
vinusankars/beast/ar_evaluate.py
pointer only (licence: NONE) · get_code("1dee415db79120bc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vinusankars/beast 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.

list_of_strings Ran
ran; our contract draft was wrong, not the code
vinusankars/beast/ar_self_attack.py
pointer only (licence: NONE) · get_code("19ee4683eda506c6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vinusankars/beast 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.

sample_top_p Ran
ran; our contract draft was wrong, not the code
vinusankars/beast/arutils.py
pointer only (licence: NONE) · get_code("e26c6aee991a471a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vinusankars/beast 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_generation Not yet run
unverified (harvested, no recorded run)
vinusankars/beast/ar_evaluate.py
pointer only (licence: NONE) · get_code("b321468159ec0e76")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, vinusankars/beast 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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
list_of_strings 8 other papers
3 dated earlier, 5 later
2112.05745 (2021-12)
A Simple and Efficient Sampling-based Algorithm for General Reachability Analysis
2308.13320 (2023-08)
Fine-tuning can cripple your foundation model; preserving features may be the solution
2310.19046 (2023-10)
Large Language Models as Evolutionary Optimizers
and 5 more not named here

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

In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability of adversarial prompts. The computational efficiency of BEAST facilitates us to investigate its applications on LMs for jailbreaking, eliciting hallucinations, and privacy attacks. Our gradient-free targeted attack can jailbreak aligned LMs with high attack success rates within one minute. For instance, BEAST can jailbreak Vicuna-7B-v1.5 under one minute with a success rate of 89% when compared to a gradient-based baseline that takes over an hour to achieve 70% success rate using a single Nvidia RTX A6000 48GB GPU. Additionally, we discover a unique outcome wherein our untargeted attack induces hallucinations in LM chatbots. Through human evaluations, we find that our untargeted attack causes Vicuna-7B-v1.5 to produce ~15% more incorrect outputs when compared to LM outputs in the absence of our attack. We also learn that 22% of the time, BEAST causes Vicuna to generate outputs that are not relevant to the original prompt. Further, we use BEAST to generate adversarial prompts in a few seconds that can boost the performance of existing membership inference attacks for LMs. We believe that our fast attack, BEAST, has the potential to accelerate research in LM security and privacy. Our codebase is publicly available at https://github.com/vinusankars/BEAST.

For agents

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

get_harvested_code_for_paper("2402.15570")
get_code_for_paper("2402.15570")
have("2402.15570")

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

curl https://syntology.ai/api/ran/2402.15570.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.15570.svg)](https://syntology.ai/paper/2402.15570)

Connect an agent — have() is free.