SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

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 internal decision logic is largely opaque to both defenders and attackers. This paper presents an exploratory case study that applies explainable artificial intelligence (XAI) techniques to analyze how Prompt Guard 2 distinguishes malicious from benign prompts. We conduct four ex

Read original source ↗ Open in workspace

recordType

paper

region

Global