HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
HE-Guardrail detects LLM jailbreaks during encrypted inference without decrypting client prompts.
Homomorphic encryption lets a server run an LLM on encrypted inputs but prevents inspection of prompts and responses, so jailbreaks can succeed invisibly. HE-Guardrail evaluates guardrails over ciphertext and homomorphically decides whether the model response is returned. Instantiations using Llama Guard, JBShield, and GradSafe closely reproduce plaintext decisions, with different security, efficiency, and utility trade-offs.
- Encrypted LLM inference hides adversarial prompts from the server.
- HE-Guardrail evaluates guardrails entirely over ciphertext.
- Instantiated with Llama Guard, JBShield, and GradSafe.
- Encrypted decisions closely match the plaintext guardrails.
- Products
- Llama GuardJBShieldGradSafe
- AI models
- Llama Guard
From the original article
1 min read at arxiv.orgHomomorphic 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.
By Byeongseo Min · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.