AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 983 results — Medium severity, no patch
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via Grappler optimizer CHECK failure

CVE-2022-23579
6.5
EPSS 0.8%
DoSSupply ChainFrameworkModel
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: memory leak via invalid graph node

CVE-2022-23578
4.3
EPSS 0.7%
DoSFrameworkInference
tensorflow3.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: null pointer deref crashes model loader

CVE-2022-23577
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer overflow in cost estimator causes DoS

CVE-2022-23576
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer overflow in cost estimator → DoS

CVE-2022-23575
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via shape inference assertion failure

CVE-2022-23572
6.5
EPSS 1.0%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUM

TensorFlow: protobuf assertion DoS via invalid tensor dtype

CVE-2022-23571
6.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: null-deref DoS via malformed protobuf tensor

CVE-2022-23570
6.5
EPSS 1.0%
DoSCode ExecutionFrameworkInference
tensorflowCWE-4763.4K3 ATLAS
MEDIUM

TensorFlow: DoS via malicious SavedModel AttrDef duplication

CVE-2022-23565
6.5
EPSS 0.5%
DoSSupply ChainFrameworkModel
tensorflow3.4K5 ATLAS
MEDIUM

TensorFlow: DoS via reachable assertion in protobuf decode

CVE-2022-23564
6.5
EPSS 0.5%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUM

TensorFlow: TOC/TOU race allows temp file hijacking

CVE-2022-23563
6.3
EPSS 0.1%
Supply ChainData LeakageCode ExecutionFrameworkTraining Data
tensorflowCWE-3673.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow TFLite: DoS via divide-by-zero in BiasAndClamp

CVE-2022-23557
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflow3.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow Lite: DoS via crafted depthwise conv model

CVE-2022-21741
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-3693.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: QuantizedMaxPool null ptr deref causes DoS

CVE-2022-21739
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-4763.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer overflow crashes process via sparse op

CVE-2022-21738
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-1903.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via malformed Bincount arguments

CVE-2022-21737
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-7543.4K3 ATLAS
MEDIUM

TensorFlow: DoS via reachable assertions in ML ops

CVE-2022-23569
6.5
EPSS 0.5%
DoSFrameworkInference
tensorflowCWE-6173.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via FractionalMaxPool div-by-zero

CVE-2022-21735
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-3693.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via MapStage non-scalar key crash

CVE-2022-21734
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-8433.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: UnravelIndex integer overflow → DoS

CVE-2022-21729
6.5
EPSS 0.8%
DoSFrameworkInference
tensorflowCWE-1903.4K3 ATLAS

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial