---
id: 8509
title: "AI Security Must Go Beyond the Model: CertiK Identifies Google EdgeTPU Vulnerabilities, Highlighting New Risks in AI Infrastructure"
source_domain: certik.com
source_url: "https://www.certik.com/blog/certik-identifies-google-edgetpu-vulnerabilities"
published_at: "2026-07-29T13:00:00Z"
tags: ["ai-security", "web3", "vulnerability-research", "android", "vulnerability", "google", "google-edgetpu", "cve-2026-0150", "cve-2026-0153", "edgetpu"]
phying_url: "https://phying.com/item/8509"
lang: en
---

# AI Security Must Go Beyond the Model: CertiK Identifies Google EdgeTPU Vulnerabilities, Highlighting New Risks in AI Infrastructure

## Summary

CertiK identified two Google EdgeTPU flaws, CVE-2026-0150 and CVE-2026-0153 (High and Critical), acknowledged in Google's June 2026 Security Bulletin, exposing security gaps in AI infrastructure.

## Intelligence Metadata

- **Sources:** certik.com
- **Published:** 2026-07-29T13:00:00Z
- **Original:** https://www.certik.com/blog/certik-identifies-google-edgetpu-vulnerabilities
- **Phying News:** https://phying.com/item/8509