الباحثون

Gustavo Betarte

المنشورات 2

نسخة أولية وصول مفتوح

Comparative Evaluation of Static Embedding Models for HTTP Request Anomaly Detection

Web applications are increasingly targeted by cyberattacks that exploit HTTP requests to evade security mechanisms. Traditional web application firewalls (WAFs) rely on rule-based approaches that often exhibit high false positive rates and limited adaptability. Recent studies have explored machine learning techniques a …

نسخة أولية وصول مفتوح

Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection

Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation through prompt injection and jailbreak attacks. Classifier-based guardrails, such as Prompt Guard 2, are widely used as a first line of defense against such attacks, but their …

المؤلفون المشاركون