FuzzLLM: A Novel and Universal Fuzzing Framework for Proactively Discovering Jailbreak Vulnerabilities in Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yao, Dongyu, Zhang, Jianshu, Harris, Ian G., Carlsson, Marcel
Formato:	Preprint
Publicado:	2023
Materias:	Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLM4Fuzz: Guided Fuzzing of Smart Contracts with Large Language Models
por: Shou, Chaofan, et al.
Publicado: (2024)

TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice
por: Goel, Aman, et al.
Publicado: (2025)

FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework
por: Béjar, Mario Rodríguez, et al.
Publicado: (2026)

WhisperFuzz: White-Box Fuzzing for Detecting and Locating Timing Vulnerabilities in Processors
por: Borkar, Pallavi, et al.
Publicado: (2024)

G-Fuzz: A Directed Fuzzing Framework for gVisor
por: Li, Yuwei, et al.
Publicado: (2024)

EmbedFuzz: High Speed Fuzzing Through Transplantation
por: Hofhammer, Florian, et al.
Publicado: (2024)

zkFuzz: Foundation and Framework for Effective Fuzzing of Zero-Knowledge Circuits
por: Takahashi, Hideaki, et al.
Publicado: (2025)

Directed Greybox Fuzzing via Large Language Model
por: Xu, Hanxiang, et al.
Publicado: (2025)

MirrorFuzz: Leveraging LLM and Shared Bugs for Deep Learning Framework APIs Fuzzing
por: Ou, Shiwen, et al.
Publicado: (2025)

FuzzSense: Towards A Modular Fuzzing Framework for Autonomous Driving Software
por: Roberts, Andrew, et al.
Publicado: (2025)

Fuzz on the Beach: Fuzzing Solana Smart Contracts
por: Smolka, Sven, et al.
Publicado: (2023)

BandFuzz: An ML-powered Collaborative Fuzzing Framework
por: Shi, Wenxuan, et al.
Publicado: (2025)

ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents
por: Wu, Jiangrong, et al.
Publicado: (2026)

Large Language Model assisted Hybrid Fuzzing
por: Meng, Ruijie, et al.
Publicado: (2024)

ProphetFuzz: Fully Automated Prediction and Fuzzing of High-Risk Option Combinations with Only Documentation via Large Language Model
por: Wang, Dawei, et al.
Publicado: (2024)

Fixing Security Vulnerabilities with AI in OSS-Fuzz
por: Zhang, Yuntong, et al.
Publicado: (2024)

Smart Contract Fuzzing Towards Profitable Vulnerabilities
por: Kong, Ziqiao, et al.
Publicado: (2025)

GoldenFuzz: Generative Golden Reference Hardware Fuzzing
por: Wu, Lichao, et al.
Publicado: (2025)

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs
por: Gong, Xueluan, et al.
Publicado: (2024)

CuFuzz: Hardening CUDA Programs through Transformation and Fuzzing
por: Singh, Saurabh, et al.
Publicado: (2026)

ReFuzz: Reusing Tests for Processor Fuzzing with Contextual Bandits
por: Chen, Chen, et al.
Publicado: (2025)

ChatHTTPFuzz: Large Language Model-Assisted IoT HTTP Fuzzing
por: Yang, Zhe, et al.
Publicado: (2024)

Prompt Fuzzing for Fuzz Driver Generation
por: Lyu, Yunlong, et al.
Publicado: (2023)

OverrideFuzz: Semantic-Aware Grammar Fuzzing for Script-Runtime Vulnerabilities
por: Qiu, Yiran
Publicado: (2026)

Harnessing Large Language Models for Seed Generation in Greybox Fuzzing
por: Shi, Wenxuan, et al.
Publicado: (2024)

LibAFL-DiFuzz: Advanced Architecture Enabling Directed Fuzzing
por: Parygina, Darya, et al.
Publicado: (2024)

PatchFuzz: Patch Fuzzing for JavaScript Engines
por: Wang, Junjie, et al.
Publicado: (2025)

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations
por: Sun, Yanbang, et al.
Publicado: (2026)

NecoFuzz: Effective Fuzzing of Nested Virtualization via Fuzz-Harness Virtual Machines
por: Ishii, Reima, et al.
Publicado: (2025)

ThreadFuzzer: Fuzzing Framework for Thread Protocol
por: Siroš, Ilja, et al.
Publicado: (2025)

Fuzzing: Randomness? Reasoning! Efficient Directed Fuzzing via Large Language Models
por: Feng, Xiaotao, et al.
Publicado: (2025)

All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching
por: Sheng, Ze, et al.
Publicado: (2025)

E-FuzzEdge: Optimizing Embedded Device Security with Scalable In-Place Fuzzing
por: Rusconi, Davide, et al.
Publicado: (2025)

LLAMAFUZZ: Large Language Model Enhanced Greybox Fuzzing
por: Zhang, Hongxiang, et al.
Publicado: (2024)

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
por: Dong, Yingkai, et al.
Publicado: (2024)

The HTTP Garden: Discovering Parsing Vulnerabilities in HTTP/1.1 Implementations by Differential Fuzzing of Request Streams
por: Kallus, Ben, et al.
Publicado: (2024)

FuzzPilot: Plateau-Triggered Recipe Validation for Structured Text Fuzzing
por: Yao, Zhiyi
Publicado: (2026)

MobFuzz: Adaptive Multi-objective Optimization in Gray-box Fuzzing
por: Zhang, Gen, et al.
Publicado: (2024)

LLM-Assisted Model-Based Fuzzing of Protocol Implementations
por: Huang, Changze, et al.
Publicado: (2025)

FuzzySQL: Uncovering Hidden Vulnerabilities in DBMS Special Features with LLM-Driven Fuzzing
por: Chen, Yongxin, et al.
Publicado: (2026)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
ui	"standard"
language	"es"
VUFIND_SESSION	"b0c4f6f4315bcd26fc070b3ab940b239"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790808204.5363 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "b0c4f6f4315bcd26fc070b3ab940b239" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"ui=standard; language=es; VUFIND_SESSION=b0c4f6f4315bcd26fc070b3ab940b239"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.216.147"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"26719"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2309_05274/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2309_05274/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790808204.5192
REQUEST_TIME	1790808204

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler