Search papers, labs, and topics across Lattice.
This paper introduces a multi-agent firewall architecture aimed at protecting sensitive data during interactions with Large Language Models (LLMs) by integrating a browser extension and a proxy for comprehensive traffic interception. The proposed system employs a hybrid approach that combines deterministic detectors with LLM-driven semantic analysis to prevent data leakage, while also allowing for future enhancements such as prompt injection evasion. Evaluation results indicate that the architecture achieves impressive F1 scores of up to 94.93% under optimal configurations, showcasing its effectiveness in safeguarding privacy in diverse environments.
Achieving up to 94.93% F1 scores, this innovative firewall architecture offers a robust solution for protecting sensitive data in LLM interactions.
While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, user-facing firewall designed to secure both web-based and programmatic LLM interactions. The architecture combines a browser extension and a proxy for total traffic interception across both HTTP(S) and WebSocket communications. At its core, a flexible multi-agent pipeline delivers data leakage prevention through a hybrid approach combining deterministic detectors with LLM-driven semantic analysis, proprietary code leakage prevention, and extensible components designed for future security enhancements such as prompt injection evasion. The framework's layered architecture enables deployment across heterogeneous environments, allowing organizations to balance computational cost, detection depth and latency. Evaluation results demonstrate it achieves F1 scores of up to 94.93% on optimal configurations.
