SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.06373 · ACL · 2024

How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs This paper contains jailbreaking contents that can be offensive in nature

Ruoxi Jia, Yi Zeng, Diyi Yang, Weiyan Shi, Jingwen Zhang, Hongpeng Lin

arXiv · PDF · Open in the Atlas

Code that ran

3 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 0 have no contract verdict; 3 failures of our instrument; 0 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/2401.06373.json · badge: /api/ran/2401.06373.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
AAAAAAsuka/LLM_defends canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
chats-lab/persuasive_jailbreaker canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
alignment_check Ran
ran; our contract draft was wrong, not the code
AAAAAAsuka/LLM_defends/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from AAAAAAsuka/llm_defends, is pointer only (licence: NONE) · get_code("297964ea6a38a8ee")
How it ran

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

build_chat_input Ran
ran; our contract draft was wrong, not the code
AAAAAAsuka/LLM_defends/utils.py
pointer only (licence: NONE); the stored copy get_code serves, from AAAAAAsuka/llm_defends, is pointer only (licence: NONE) · get_code("716676f9101e0f57")
How it ran

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

extract_content Ran
ran; our contract draft was wrong, not the code
chats-lab/persuasive_jailbreaker/PAP_Better_Incontext_Sample/mutation_utils.py
code served (permissive licence) · get_code("04e9ab3c39976275")
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 str. 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

def extract_content(tag, text):
    start_idx = text.find(tag)
    if start_idx == -1:
        return None
    content_after_tag = text[start_idx + len(tag):].strip()
    end_idx = text.find('#', start_idx + 1)
    return content_after_tag if end_idx == -1 else content_after_tag[:end_idx].strip()


ARGS = {
    "tag": "<content>",
    "text": "<content>This is the extracted text# this should be ignored"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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

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, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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
alignment_check 1 other paper
1 later
2404.13968 (2024-04)
Protecting Your LLMs with Information Bottleneck
build_chat_input 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

Most traditional AI safety research views models as machines and centers on algorithmfocused attacks developed by security experts. As large language models (LLMs) become increasingly common and competent, non-expert users can also impose risks during daily interactions. Observing this, we shift the perspective, by treating LLMs as human-like communicators to examine the interplay between everyday language interaction and AI safety. Specifically, we study how to persuade LLMs to jailbreak them. First, we propose a persuasion taxonomy derived from decades of social science research. Then, we apply the taxonomy to automatically generate persuasive adversarial prompts (PAP) to jailbreak LLMs. Results show that persuasion significantly increases the jailbreak risk across all risk categories: PAP consistently achieves an attack success rate of over 92% on Llama-2-7b-Chat, GPT-3.5, and GPT-4 in 10 trials, surpassing recent algorithm-focused attacks. On the defense side, we explore various mechanisms against PAP, find a significant gap in existing defenses, and advocate for more fundamental solutions for AI safety 1 . * Lead authors. Corresponding Y. Zeng, W. Shi, R. Jia † Co-supervised the project, listed alphabetically. The work was done while W.S. was at Stanford. 1 We have informed Meta and OpenAI of our findings. For safety concerns, we only publicly release our persuasion taxonomy at https://github.com/CHATS-lab/ persuasive_jailbreaker. Researchers can apply for the jailbreaking data upon review.

For agents

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

get_harvested_code_for_paper("2401.06373")
get_code_for_paper("2401.06373")
have("2401.06373")

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

curl https://syntology.ai/api/ran/2401.06373.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.06373.svg)](https://syntology.ai/paper/2401.06373)

Connect an agent — have() is free.