SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.16192 · 2024

Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing

arXiv · PDF · Open in the Atlas

Code that ran

2 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 0 have no contract verdict; 2 failures of our instrument; 4 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/2402.16192.json · badge: /api/ran/2402.16192.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
ucsb-nlp-chang/semanticsmooth canonical (classifier label)
classifier basis not recorded on the link
2 ran · 4 no recorded run
FunctionStatusWhere it lives
default_hparams Ran
ran; our contract draft was wrong, not the code
ucsb-nlp-chang/semanticsmooth/lib/hparams_registry.py
code served (permissive licence) · get_code("b5252ac83a7c46c3")
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 dict. 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 os
import torch

# Set up environment variables that the function checks
os.environ['PROMPT_TAMPLATE_DIR'] = 'data/prompt-template-llama'
os.environ['VIRTUAL_LLM_URL'] = 'http://localhost:10000/v1/'

ARGS = {
    'defense': 'SmoothLLM',
    'attack': 'GCG',
    'target': 'llama-vllm'
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
mean_pooling Ran
ran; our contract draft was wrong, not the code
ucsb-nlp-chang/semanticsmooth/lib/ensemble_policy.py
pointer only (licence: MIT); the stored copy get_code serves, from dengyang17/llm-proactive, is pointer only (licence: NONE) · get_code("77f69af078e09830")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dengyang17/llm-proactive, and GitHub detected no licence in that repository 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.

create_defense_from_config Not yet run
unverified (harvested, no recorded run)
ucsb-nlp-chang/semanticsmooth/lib/defenses.py
code served (permissive licence) · get_code("4190042b24d3f36b")
How it ran

no invocation recorded.

create_ensemble_policy_model Not yet run
unverified (harvested, no recorded run)
ucsb-nlp-chang/semanticsmooth/lib/ensemble_policy.py
code served (permissive licence) · get_code("8cecc2a857c57545")
How it ran

no invocation recorded.

create_perturbation Not yet run
unverified (harvested, no recorded run)
ucsb-nlp-chang/semanticsmooth/lib/perturbations.py
code served (permissive licence) · get_code("94699190b22cdf4c")
How it ran

no invocation recorded.

merge_cmd_configs Not yet run
unverified (harvested, no recorded run)
ucsb-nlp-chang/semanticsmooth/lib/hparams_registry.py
code served (permissive licence) · get_code("b58775a1975c2aaa")
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, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 6 later) and 0 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
mean_pooling 22 other papers
8 dated earlier, 2 the same month, 12 later · 1 only as an assembly brick
2206.04624 (2022-06)
Factuality Enhanced Language Models for Open-Ended Text Generation
2023.findings-emnlp.540 (2023 (year only))
Open-ended Commonsense Reasoning with Unrestricted Answer Scope
2302.05698 (2023-02)
Compositional Exemplars for In-context Learning
and 19 more not named here
create_defense_from_config 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck
create_ensemble_policy_model 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck
create_perturbation 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck
default_hparams 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck
merge_cmd_configs 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck

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

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat models, there do not exist defenses that provide robustness against semantic attacks and avoid unfavorable trade-offs between robustness and nominal performance. To meet this need, we propose SEMANTICSMOOTH, a smoothing-based defense that aggregates the predictions of multiple semantically transformed copies of a given input prompt. Experimental results demonstrate that SEMANTICSMOOTH achieves state-of-the-art robustness against GCG, PAIR, and AutoDAN attacks while maintaining strong nominal performance on instruction following benchmarks such as InstructionFollowing and AlpacaEval. The codes will be publicly available at https://github.com/UCSB-NLP-Chang/SemanticSmooth.

For agents

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

get_harvested_code_for_paper("2402.16192")
get_code_for_paper("2402.16192")
have("2402.16192")

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

curl https://syntology.ai/api/ran/2402.16192.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.16192.svg)](https://syntology.ai/paper/2402.16192)

Connect an agent — have() is free.