Year: 2026
Type: conference-paper
Abstract: Large Language Models (LLMs) are increasingly deployed in high-impact scenarios, raising concerns about their safety and security.Despite existing defense mechanisms, LLMs remain vulnerable to adversarial attacks.This paper introduces the novel attack-agnostic pipeline SENTRY (semantic entropy-based attack recognition system) for detecting such attacks by leveraging the predictive entropy of model outputs.We quantify this through the Token-Level Shifting Attention to Relevance (TokenSAR) score, a weighted token entropy measurement.Our approach dynamically identifies adversarial inputs without relying on prior knowledge of attack specifications.It requires only ten newly generated tokens, making it a computationally efficient and adaptable solution.We evaluate the pipeline on multiple state-of-the-art models, including Llama, Vicuna, Falcon, Deep Seek, and Mistral, using a diverse set of adversarial prompts generated via the h4rm31 framework.Experimental results demonstrate a clear separation in TokenSAR scores between benign, malicious, and adversarial prompts.This distinction enables effective threshold-based classification, achieving robust detection performance across various model architectures.Our method outperforms traditional defenses in terms of adaptability and resource efficiency.
Institution: Ostbayerische Technische Hochschule Amberg-Weiden
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7140131249