AI Threat Alert
AI Threat Alert tracks 432 known AI/ML vulnerabilities affecting Google products — each enriched with CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis. Browse every Google CVE below, sorted by severity and recency.
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| HIGH | CVE-2021-41225 | TensorFlow Grappler: uninitialized var, local priv-esc | tensorflow | 7.8 |
| MEDIUM | CVE-2021-41227 | TensorFlow: OOB read in ImmutableConst leaks memory | tensorflow | 5.5 |
| HIGH | CVE-2021-41228 | TensorFlow: eval() in saved_model_cli allows RCE | tensorflow | 7.8 |
| HIGH | CVE-2022-21726 | TensorFlow: heap OOB read in Dequantize op allows RCE | tensorflow | 8.8 |
| HIGH | CVE-2022-21727 | TensorFlow: Dequantize integer overflow, RCE risk | tensorflow | 8.8 |
| HIGH | CVE-2022-21728 | TensorFlow: heap OOB read in ReverseSequence op | tensorflow | 8.1 |
| HIGH | CVE-2022-21730 | TensorFlow: OOB read leaks heap memory, enables DoS | tensorflow | 8.1 |
| MEDIUM | CVE-2022-21731 | TensorFlow: ConcatV2 type confusion enables remote DoS | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21732 | TensorFlow: ThreadPoolHandle DoS via memory exhaustion | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21733 | TensorFlow: StringNGrams integer overflow enables OOM DoS | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21736 | TensorFlow: NULL deref DoS via SparseTensorSliceDataset | tensorflow | 6.5 |
| MEDIUM | CVE-2022-23567 | TensorFlow: integer overflow DoS in sparse tensor ops | tensorflow | 6.5 |
| MEDIUM | CVE-2022-23568 | TensorFlow: integer overflow DoS in sparse tensor ops | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21725 | TensorFlow: DoS via div-by-zero in conv cost estimator | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21729 | TensorFlow: UnravelIndex integer overflow → DoS | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21734 | TensorFlow: DoS via MapStage non-scalar key crash | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21735 | TensorFlow: DoS via FractionalMaxPool div-by-zero | tensorflow | 6.5 |
| MEDIUM | CVE-2022-23569 | TensorFlow: DoS via reachable assertions in ML ops | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21737 | TensorFlow: DoS via malformed Bincount arguments | tensorflow | 6.5 |
| MEDIUM | CVE-2022-21738 | TensorFlow: integer overflow crashes process via sparse op | tensorflow | 6.5 |
Frequently asked questions
How many known vulnerabilities affect Google?
432 AI/ML CVEs affecting Google products are tracked, sourced from NVD and GitHub Advisory.
What Google products are affected?
The CVEs below map to the Google AI/ML packages and tools tracked by AI Threat Alert; open any CVE to see the affected components and versions.
Where does the Google vulnerability data come from?
Data is sourced from NVD and GitHub Advisory, then enriched with CVSS severity, EPSS exploit probability, and patch status for each CVE.
How can I monitor Google for new vulnerabilities?
AI Threat Alert tracks Google continuously; a Pro subscription adds breaking alerts when new CVEs affecting Google are published.
How do I assess Google's security exposure?
Each CVE below carries CVSS severity and exploitation signals, so you can review the highest-severity Google issues first and judge the exposure for your stack.