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 1961 results — Active exploitation
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB read in quantize ops, DoS+leak

CVE-2021-41205
7.1
EPSS 0.2%
DoSData LeakageFrameworkTraining DataInference
tensorflowCWE-1253.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via Grappler constant folding segfault

CVE-2021-41204
5.5
EPSS 0.1%
DoSFrameworkInference
tensorflowCWE-8243.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: malformed checkpoint triggers overflow/crash

CVE-2021-41203
7.8
EPSS 0.2%
Supply ChainCode ExecutionDoSFrameworkTraining Data
tensorflowCWE-1903.4K4 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: heap OOB read in SparseCountSparseOutput

CVE-2021-41210
7.1
EPSS 0.2%
Data ExtractionCode ExecutionDoSFrameworkTraining Data
tensorflowCWE-1253.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: uninitialized var in Einsum allows local RCE

CVE-2021-41201
7.8
EPSS 0.2%
Code ExecutionFrameworkInference
tensorflowCWE-8243.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS crash in tf.summary file writer

CVE-2021-41200
5.5
EPSS 0.2%
DoSFrameworkTraining Data
tensorflowCWE-6173.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: tf.image.resize integer overflow DoS

CVE-2021-41199
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflowCWE-1903.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: tf.tile integer overflow crashes ML process

CVE-2021-41198
5.5
EPSS 0.2%
DoSFrameworkInferenceTraining Data
tensorflowCWE-1903.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer overflow in tensor dims causes DoS

CVE-2021-41197
5.5
EPSS 0.3%
DoSFrameworkInference
tensorflowCWE-1903.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer underflow crashes Keras pooling layers

CVE-2021-41196
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflowCWE-1913.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: integer overflow in segment ops causes DoS

CVE-2021-41195
5.5
EPSS 0.2%
DoSFramework
tensorflowCWE-1903.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow/Keras: RCE via YAML model deserialization

CVE-2021-37678
8.8
EPSS 0.4%
Code ExecutionSupply ChainFrameworkModel
tensorflowCWE-5023.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via division by zero in conv ops

CVE-2021-37675
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
CRITICALEXPLOIT AVAIL

TensorFlow: path traversal in get_file allows file overwrite

CVE-2021-35958
9.1
EPSS 1.9%
Supply ChainCode ExecutionFrameworkTraining Data
tensorflowCWE-223.4K4 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via invalid SparseCount op args

CVE-2021-29619
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS crash via tf.transpose complex+conjugate

CVE-2021-29618
5.5
EPSS 0.2%
DoSFrameworkInference
tensorflow3.4K3 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: DoS via CHECK-fail in strings.substr

CVE-2021-29617
5.5
EPSS 0.2%
DoSFramework
tensorflowCWE-7553.4K2 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: null ptr deref in graph optimizer

CVE-2021-29616
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkInference
tensorflowCWE-4763.4K2 ATLAS
MEDIUMEXPLOIT AVAIL

TensorFlow: uncontrolled recursion DoS in ParseAttrValue

CVE-2021-29615
5.5
EPSS 0.2%
DoSSupply ChainFrameworkInference
tensorflow3.4K3 ATLAS
HIGHEXPLOIT AVAIL

TensorFlow: OOB write in decode_raw crashes interpreter

CVE-2021-29614
7.8
EPSS 0.2%
Code ExecutionDoSFrameworkTraining Data
tensorflowCWE-7873.4K3 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