# Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts

arXiv: https://arxiv.org/abs/2510.22628 · HTML: https://mlsanity.com/paper/2510.22628/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Jailbreaking, one of 12 directions in LLM safety and security.
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Placed in

- LLM safety and security / [Jailbreaking](https://mlsanity.com/safety/jailbreaking/)

## Builds on (most cited first, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [Red Teaming Language Models with Language Models](https://mlsanity.com/paper/2202.03286/) (2022)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://mlsanity.com/paper/2503.21460/) (2025)
- [Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks](https://mlsanity.com/paper/2310.10844/) (2023)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks](https://mlsanity.com/paper/2403.04783/) (2024)
- [Unleashing the potential of prompt engineering for large language models](https://mlsanity.com/paper/2310.14735/) (2023)
- [JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models](https://mlsanity.com/paper/2407.01599/) (2024)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation](https://mlsanity.com/paper/2502.07557/) (2025)
- [Privacy in Large Language Models: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2310.10383/) (2023)
- [A Cross-Language Investigation into Jailbreak Attacks in Large Language Models](https://mlsanity.com/paper/2401.16765/) (2024)
- [A Survey on Large Language Models with Multilingualism: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.10936/) (2024)
- [Jailbreaking and Mitigation of Vulnerabilities in Large Language Models](https://mlsanity.com/paper/2410.15236/) (2024)
- [A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions](https://mlsanity.com/paper/2405.14487/) (2024)
- [A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations](https://mlsanity.com/paper/2502.05224/) (2025)
- [Goal-guided Generative Prompt Injection Attack on Large Language Models](https://mlsanity.com/paper/2404.07234/) (2024)
- [from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors](https://mlsanity.com/paper/2503.00038/) (2025)
- [Attack and defense techniques in large language models: A survey and new perspectives](https://mlsanity.com/paper/2505.00976/) (2025)
- [Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics](https://mlsanity.com/paper/2505.18658/) (2025)
- [Red Teaming Contemporary AI Models: Insights from Spanish and Basque Perspectives](https://mlsanity.com/paper/2503.10192/) (2025)
- [Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms](https://mlsanity.com/paper/2409.07989/) (2024)
- [The Role of Transformer Models in Advancing Blockchain Technology: A Systematic Survey](https://mlsanity.com/paper/2409.02139/) (2024)
- [DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech](https://mlsanity.com/paper/2410.04188/) (2024)
- [Algorithms for Adversarially Robust Deep Learning](https://mlsanity.com/paper/2509.19100/) (2025)

## Built on by (most cited first, 1 of 1)

- [One Jailbreak, Many Tongues: Learning Language-Insensitive Intention Representations for Multilingual Jailbreak Detection](https://mlsanity.com/paper/2606.11202/) (2026)

## Abstract (arXiv)

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with FAISS-indexed SBERT embedding representations that capture the semantic meaning of prompts, combined with fine-tuned transformer classifiers, which are machine learning models specialized for distinguishing between benign and adversarial language inputs. It identifies adversarial prompts in both direct and obfuscated attack vectors. A core innovation is the classifier-retriever fusion module, which dynamically computes context-aware risk scores that estimate how likely a prompt is to be adversarial based on its content and context. The framework ensures multilingual resilience with a language-agnostic preprocessing layer. This component automatically translates non-English prompts into English for semantic evaluation, enabling consistent detection across over 100 languages. The system includes a HITL feedback loop, where decisions made by the automated system are reviewed by human experts for continual learning and rapid adaptation under adversarial pressure. Sentra-Guard maintains an evolving dual-labeled knowledge base of benign and malicious prompts, enhancing detection reliability and reducing false positives. Evaluation results show a 99.96% detection rate (AUC = 1.00, F1 = 1.00) and an attack success rate (ASR) of only 0.004%. This outperforms leading baselines such as LlamaGuard-2 (1.3%) and OpenAI Moderation (3.7%). Unlike black-box approaches, Sentra-Guard is transparent, fine-tunable, and compatible with diverse LLM backends. Its modular design supports scalable deployment in both commercial and open-source environments. The system establishes a new state-of-the-art in adversarial LLM defense.