Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yan, Hao, Vaidya, Swapneel Suhas, Zhang, Xiaokuan, Yao, Ziyu
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Software Engineering
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Improving Automated Secure Code Reviews: A Synthetic Dataset for Code Vulnerability Flaws
di: Centellas-Claros, Leonardo, et al.
Pubblicazione: (2025)

Detect Repair Verify for Securing LLM Generated Code: A Multi-Language Empirical Study
di: Cheng, Cheng
Pubblicazione: (2026)

LLM-Based Test-Driven Interactive Code Generation: User Study and Empirical Evaluation
di: Fakhoury, Sarah, et al.
Pubblicazione: (2024)

Write Your Own CodeChecker: An Automated Test-Driven Checker Development Approach with LLMs
di: Liu, Jun, et al.
Pubblicazione: (2024)

An Empirical Security Evaluation of LLM-Generated Cryptographic Rust Code
di: Elsayed, Mohamed, et al.
Pubblicazione: (2026)

Toward Effective Secure Code Reviews: An Empirical Study of Security-Related Coding Weaknesses
di: Charoenwet, Wachiraphan, et al.
Pubblicazione: (2023)

Understanding Specification-Driven Code Generation with LLMs: An Empirical Study Design
di: Rosa, Giovanni, et al.
Pubblicazione: (2026)

GitHub's Copilot Code Review: Can AI Spot Security Flaws Before You Commit?
di: Amro, Amena, et al.
Pubblicazione: (2025)

An Empirical Study of Interaction Smells in Multi-Turn Human-LLM Collaborative Code Generation
di: Zhang, Binquan, et al.
Pubblicazione: (2026)

Do AI Coding Agents Log Like Humans? An Empirical Study
di: Ouatiti, Youssef Esseddiq, et al.
Pubblicazione: (2026)

Scaling Test-Driven Code Generation from Functions to Classes: An Empirical Study
di: Liang, Yunhao, et al.
Pubblicazione: (2026)

An Empirical Study of Static Analysis Tools for Secure Code Review
di: Charoenwet, Wachiraphan, et al.
Pubblicazione: (2024)

A Large-Scale Empirical Study of AI-Generated Code in Real-World Repositories
di: Mao, Tianhao, et al.
Pubblicazione: (2026)

AI builds, We Analyze: An Empirical Study of AI-Generated Build Code Quality
di: Ghammam, Anwar, et al.
Pubblicazione: (2026)

On the Effectiveness of Training Data Optimization for LLM-based Code Generation: An Empirical Study
di: Kuang, Shiqi, et al.
Pubblicazione: (2025)

An Empirical Study on Code Review Activity Prediction and Its Impact in Practice
di: Olewicki, Doriane, et al.
Pubblicazione: (2024)

An Empirical Study of LLM-Based Code Clone Detection
di: Zhu, Wenqing, et al.
Pubblicazione: (2025)

Fixing Your Own Smells: Adding a Mistake-Based Familiarisation Step When Teaching Code Refactoring
di: Tan, Ivan, et al.
Pubblicazione: (2024)

Fixing Function-Level Code Generation Errors for Foundation Large Language Models
di: Wen, Hao, et al.
Pubblicazione: (2024)

Toward Interactive Optimization of Source Code Differences: An Empirical Study of Its Performance
di: Yagi, Tsukasa, et al.
Pubblicazione: (2024)

An Empirical Study on Automatically Detecting AI-Generated Source Code: How Far Are We?
di: Suh, Hyunjae, et al.
Pubblicazione: (2024)

Rethinking Code Review Workflows with LLM Assistance: An Empirical Study
di: Aðalsteinsson, Fannar Steinn, et al.
Pubblicazione: (2025)

Debt Behind the AI Boom: A Large-Scale Empirical Study of AI-Generated Code in the Wild
di: Liu, Yue, et al.
Pubblicazione: (2026)

Codexity: Secure AI-assisted Code Generation
di: Kim, Sung Yong, et al.
Pubblicazione: (2024)

Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generation
di: Vartziotis, Tina, et al.
Pubblicazione: (2024)

Decoding Human-LLM Collaboration in Coding: An Empirical Study of Multi-Turn Conversations in the Wild
di: Zhang, Binquan, et al.
Pubblicazione: (2025)

An Empirical Study on LLM-based Agents for Automated Bug Fixing
di: Meng, Xiangxin, et al.
Pubblicazione: (2024)

An Empirical Study of the Non-determinism of ChatGPT in Code Generation
di: Ouyang, Shuyin, et al.
Pubblicazione: (2023)

Compact Constraint Encoding for LLM Code Generation: An Empirical Study of Token Economics and Constraint Compliance
di: Tang, Hanzhang
Pubblicazione: (2026)

Code vs Serialized AST Inputs for LLM-Based Code Summarization: An Empirical Study
di: Dong, Shijia, et al.
Pubblicazione: (2026)

Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study
di: Fu, Yujia, et al.
Pubblicazione: (2023)

Security Incentivization: An Empirical Study of how Micropayments Impact Code Security
di: Rass, Stefan, et al.
Pubblicazione: (2026)

Exploring Security Practices in Infrastructure as Code: An Empirical Study
di: Verdet, Alexandre, et al.
Pubblicazione: (2023)

To Err is AI : A Case Study Informing LLM Flaw Reporting Practices
di: McGregor, Sean, et al.
Pubblicazione: (2024)

Engineering Pitfalls in AI Coding Tools: An Empirical Study of Bugs in Claude Code, Codex, and Gemini CLI
di: Zhang, Ruixin, et al.
Pubblicazione: (2026)

Quantum-Guided Test Case Minimization for LLM-Based Code Generation
di: Zhang, Huixiang, et al.
Pubblicazione: (2025)

Detect--Repair--Verify for LLM-Generated Code: A Multi-Language, Multi-Granularity Empirical Study
di: Cheng, Cheng
Pubblicazione: (2026)

Failure-Aware Enhancements for Large Language Model (LLM) Code Generation: An Empirical Study on Decision Framework
di: Shen, Jianru, et al.
Pubblicazione: (2026)

Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests
di: Cynthia, Shamse Tasnim, et al.
Pubblicazione: (2026)

Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
di: Islam, Nafis Tanveer, et al.
Pubblicazione: (2024)

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
language	"it"
VUFIND_SESSION	"c5f4bfc6673b8d1f8487bab30d1bb88f"
ui	"standard"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790883559.3804 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "c5f4bfc6673b8d1f8487bab30d1bb88f" ]`]
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	"language=it; VUFIND_SESSION=c5f4bfc6673b8d1f8487bab30d1bb88f; ui=standard"
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	"216.73.217.142"
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	"12322"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2506_23034/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2506_23034/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790883559.3719
REQUEST_TIME	1790883559

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler