SOURCE-LINKED INTELLIGENCE

HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Homomorphic encryption (HE) has emerged as a promising approach to privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-based PPML, a client submits an encrypted input to the server, which evaluates models such as large language models (LLMs) without access to the underlying plaintext. However, we identify a critical security vulnerability in this setting: HE-LLM inference is vulnerable to malicious clients that submit adversarial prompts, such as jailbreak attacks. The same confidentiality that protects benign clients also prevents the server fr

Read original source ↗ Open in workspace

recordType

paper

region

Global