PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gasmi, Tarek, Guesmi, Ramzi, Aloui, Mootez, Bennaceur, Jihene
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912501101232128
author Gasmi, Tarek
Guesmi, Ramzi
Aloui, Mootez
Bennaceur, Jihene
author_facet Gasmi, Tarek
Guesmi, Ramzi
Aloui, Mootez
Bennaceur, Jihene
contents Static benchmarks fail to capture LLM vulnerabilities emerging through community experimentation in online forums. We present PrompTrend, a system that collects vulnerability data across platforms and evaluates them using multidimensional scoring, with an architecture designed for scalable monitoring. Cross-sectional analysis of 198 vulnerabilities collected from online communities over a five-month period (January-May 2025) and tested on nine commercial models reveals that advanced capabilities correlate with increased vulnerability in some architectures, psychological attacks significantly outperform technical exploits, and platform dynamics shape attack effectiveness with measurable model-specific patterns. The PrompTrend Vulnerability Assessment Framework achieves 78% classification accuracy while revealing limited cross-model transferability, demonstrating that effective LLM security requires comprehensive socio-technical monitoring beyond traditional periodic assessment. Our findings challenge the assumption that capability advancement improves security and establish community-driven psychological manipulation as the dominant threat vector for current language models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_19185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models
Gasmi, Tarek
Guesmi, Ramzi
Aloui, Mootez
Bennaceur, Jihene
Cryptography and Security
Artificial Intelligence
Static benchmarks fail to capture LLM vulnerabilities emerging through community experimentation in online forums. We present PrompTrend, a system that collects vulnerability data across platforms and evaluates them using multidimensional scoring, with an architecture designed for scalable monitoring. Cross-sectional analysis of 198 vulnerabilities collected from online communities over a five-month period (January-May 2025) and tested on nine commercial models reveals that advanced capabilities correlate with increased vulnerability in some architectures, psychological attacks significantly outperform technical exploits, and platform dynamics shape attack effectiveness with measurable model-specific patterns. The PrompTrend Vulnerability Assessment Framework achieves 78% classification accuracy while revealing limited cross-model transferability, demonstrating that effective LLM security requires comprehensive socio-technical monitoring beyond traditional periodic assessment. Our findings challenge the assumption that capability advancement improves security and establish community-driven psychological manipulation as the dominant threat vector for current language models.
title PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2507.19185