Wiz Research finds architecture risks that may compromise AI-as-a-Service providers and consequently risk customer data; works with Hugging Face on mitigations

Published

2024-04-04 15:55

Collected

2026-08-29 01:33

---
id: 7178
title: "Wiz Research finds architecture risks that may compromise AI-as-a-Service providers and consequently risk customer data; works with Hugging Face on mitigations"
source_domain: wiz.io
source_url: "https://www.wiz.io/blog/wiz-and-hugging-face-address-risks-to-ai-infrastructure"
published_at: "2024-04-04T15:55:05Z"
tags: ["ai-security", "cloud-security", "container-security", "hugging-face", "threat-research", "tenant-isolation"]
phying_url: "https://phying.com/item/7178"
lang: en
---

# Wiz Research finds architecture risks that may compromise AI-as-a-Service providers and consequently risk customer data; works with Hugging Face on mitigations

## Summary

Wiz Research shows how a malicious model plus container escape could grant cross-tenant access on AI-as-a-Service platforms, and details its joint mitigations with Hugging Face.

## Intelligence Metadata

- **Sources:** wiz.io
- **Published:** 2024-04-04T15:55:05Z
- **Original:** https://www.wiz.io/blog/wiz-and-hugging-face-address-risks-to-ai-infrastructure
- **Phying News:** https://phying.com/item/7178