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:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 4307 results

InsydeH2O: UEFI firmware stack overflow enables RCE

CVE-2021-42059

Code ExecutionInference

InsydeH2O UEFI: SMM memory corruption escalates to Ring -2

CVE-2021-43615

Code ExecutionInference

InsydeH2O: SMM callout allows arbitrary code execution

CVE-2021-41841

Code ExecutionInference

InsydeH2O UEFI: SMM privilege escalation (not AI-related)

CVE-2020-5953

Code ExecutionInference

InsydeH2O UEFI: SMM callout enables privilege escalation

CVE-2022-24069

Code ExecutionInferenceTraining Data

Insyde H2O: SMM memory corruption escalates privileges

CVE-2021-43522

Code ExecutionInference

InsydeH2O firmware: unchecked SMM buffer enables ring -2 exploit

CVE-2021-45971

Code ExecutionInference

InsydeH2O UEFI: SMM buffer flaw enables privesc

CVE-2021-45969

Code ExecutionSupply ChainInference

InsydeH2O: SMM buffer validation flaw enables priv-esc

CVE-2021-45970

Code ExecutionDoSInference

HIGHEXPLOIT AVAIL

pytorch-lightning: deserialization RCE via malicious checkpoint

CVE-2021-4118

Code ExecutionSupply ChainFrameworkTraining Data

pytorch_lightning26.1K4 ATLAS

HIGHEXPLOIT AVAILSCANNER

Gradio: path traversal exposes host filesystem to users

CVE-2021-43831

Data ExtractionPrivacy ViolationFrameworkInference

gradioCWE-227354 ATLAS

HIGHEXPLOIT AVAIL

Sockeye: unsafe YAML load RCE via model config file

CVE-2021-43811

Supply ChainCode ExecutionFrameworkModel

nbdime: stored XSS in Jupyter notebook diff viewer

CVE-2021-41134

Code ExecutionData ExtractionFramework

HIGHEXPLOIT AVAIL

TensorFlow: eval() in saved_model_cli allows RCE

CVE-2021-41228

Code ExecutionSupply ChainFrameworkTraining Data

tensorflowCWE-943.4K3 ATLAS

MEDIUMEXPLOIT AVAIL

TensorFlow: OOB read in ImmutableConst leaks memory

CVE-2021-41227

Data ExtractionSupply ChainFrameworkInference

tensorflowCWE-1253.4K4 ATLAS

HIGHEXPLOIT AVAIL

TensorFlow Grappler: uninitialized var, local priv-esc

CVE-2021-41225

Code ExecutionSupply ChainFrameworkTraining Data

tensorflow3.4K3 ATLAS

MEDIUMEXPLOIT AVAIL

TensorFlow: SplitV negative arg segfault crashes process

CVE-2021-41222

DoSFrameworkInference

tensorflow3.4K3 ATLAS

HIGHEXPLOIT AVAIL

TensorFlow: CuDNN heap overflow, local code execution

CVE-2021-41221

Code ExecutionFrameworkTraining Data

tensorflowCWE-7873.4K3 ATLAS

HIGHEXPLOIT AVAIL

TensorFlow: use-after-free in async collective ops

CVE-2021-41220

Code ExecutionModel PoisoningFrameworkTraining Data

tensorflow3.4K3 ATLAS

HIGHEXPLOIT AVAIL

TensorFlow: heap overflow in Transpose via negative perm

CVE-2021-41216

Code ExecutionFramework

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