Jul 2026· International Conference on Artificial Intelligence Testing· pp. 84-87· 0 citations· 29 references
Abstract
The increasing deployment of Large Language Models (LLMs) in critical infrastructure has introduced a class of security risks that remain insufficiently characterised and poorly tooled in practice. Attack vectors including prompt injection, jailbreaking, code execution facilitation, covert data exfiltration, and training data poisoning present quantifiable threats to systems that rely on LLM outputs, yet no lightweight, provider-agnostic tool exists to measure these risks systematically. This paper presents VectorSec, an open-source, web-based LLM security scanner built with Python and Dash. The tool executes a structured test suite of 320 adversarial prompts spanning 16 vulnerability categories aligned with the OWASP Top 10 for LLMs. Each response is scored through a four-stage pipeline combining pattern matching, sentiment analysis, semantic similarity, and secondary LLM verification. Evaluation across three open-source models demonstrates that pattern-matching-only filtering misses approximately 15% of High and Critical findings that semantic verification correctly identifies, motivating the multi-layer design. VectorSec provides interactive dashboard reporting, real-time progress tracking, and audit-ready PDF and CSV exports, lowering the barrier to structured LLM security assessment in operational settings.
Large language models (LLMs) embedded in enterprise workflows cannot structurally distinguish legitimate instructions from adversarial ones in the same token stream, making prompt injection OWASP's top LLM risk for two consecutive editions a persistent threat across direct and indirect vectors. This paper presents PromptShield-RT, a layered, real-time, model-agnostic framework combining input normalization and provenance tagging, lexical-heuristic pattern matching, a statistical classifier, structural anomaly features, and calibrated risk fusion, with policy-driven mitigation (allow/sanitize/quarantine/block) and an explainable, adaptive-feedback mechanism for SOC workflows. We construct an original evaluation corpus, SynPI-Bench (n = 450, six categories), and a template-disjoint held-out generalization set (n = 31) with novel phrasings, obfuscation encodings, and adversarial hard-negative benign text. Using template-grouped 5-fold cross-validation, the fused pipeline achieves 92.4% accuracy (F1 = 0.930, AUC = 0.990), outperforming heuristic-only (57.0%) and naive-averaged (59.2%) baselines, while a lexical classifier reaches 85.9% with lower precision. We report a pronounced generalization gap on the held-out set (48.4% accuracy, 90% false-positive rate on hard negatives), quantifying a known limitation of surface-lexical defenses. The pipeline achieves sub-millisecond P95 latency (0.266 ms), within typical 50 ms enterprise SLAs. We situate PromptShield-RT relative to structural, architectural, and guardrail-product defenses, arguing for layered, defense-in-depth architectures, with reproducible code provided.
Fatimah Alhamzawi· Al-Noor Journal of Engineeri...· 0 citations
The findings confirm that an accessible, accurate, and AI-augmented vulnerability scanner can be constructed for educational and entry-level use within a deliberately bounded scope, lowering the expertise barrier for web application security assessment.
This study proposes an automated, human-independent, and adaptive approach leveraging GFlowNets to identify LLM vulnerabilities by utilizing one large language model to test another, and introduces a model capable of generating attack inputs in the Turkish language.
Berkay Ozcam, Irem Onen, M. Amasyalı et al.· 0 citations
The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption. However, this escalating trend has introduced significant security vulnerabilities, necessitating the identification and mitigation of flaws arising from malicious exploitation. Red teaming assessments, conducted to evaluate model robustness through diverse adversarial inputs, are essential for exposing security risks and implementing countermeasures. Currently, red teaming is performed either manually by experts or automatically using predefined attack datasets. Nevertheless, manual testing remains time-consuming, while existing automated methods suffer from limited creativity due to their inherent dependency on fixed datasets. In this study, we propose an automated, human-independent, and adaptive approach leveraging GFlowNets to identify LLM vulnerabilities by utilizing one large language model to test another. Within this framework, an attacker model is trained against a specified victim model to perform automated red teaming and provide a quantitative robustness score. This research aims to generate more effective adversarial attacks in English compared to existing benchmarks and, as a novel contribution to the literature, introduces a model capable of generating attack inputs in the Turkish language.
Berkay Özçam, İrem Önen, E. I. Tatli et al.· Signal Processing and Commun...· 0 citations
Command injection vulnerabilities remain a significant security threat in dynamic languages such as Python, particularly in widely used open-source projects. Recent advances in large language models (LLMs) have shown strong potential in code-related tasks, motivating their application to vulnerability detection.In this paper, we evaluate LLM-based approaches for detecting command injection vulnerabilities and generating security tests. We apply our method to six widely used GitHub projects—Django, Flask, TensorFlow, Scikit-learn, PyTorch, and LangChain—covering over 50,000-star repositories with broad real-world usage. Our study analyzes the effectiveness of LLMs in terms of detection accuracy, efficiency, and practical applicability.We further compare multiple LLMs to assess their relative performance in vulnerability detection and test generation. The results demonstrate that LLM-based approaches can effectively identify vulnerabilities in both complete and fragmented code while providing executable security tests for validation. Our findings highlight the strengths and limitations of LLMs and offer practical insights for leveraging them to enhance automated software security testing.
