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
3,591

AI/ML CVEs Tracked

481

Critical

96

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3591 results
MEDIUM EXPLOIT AVAIL

TensorFlow: UnravelIndex integer overflow → DoS

CVE-2022-21729
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-190 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: DoS via div-by-zero in conv cost estimator

CVE-2022-21725
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-369 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: integer overflow DoS in sparse tensor ops

CVE-2022-23568
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-190 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: integer overflow DoS in sparse tensor ops

CVE-2022-23567
6.5
EPSS 1.1%
DoS Framework Inference
tensorflow CWE-190 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: NULL deref DoS via SparseTensorSliceDataset

CVE-2022-21736
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-476 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: StringNGrams integer overflow enables OOM DoS

CVE-2022-21733
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-190 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: ThreadPoolHandle DoS via memory exhaustion

CVE-2022-21732
6.5
EPSS 0.8%
DoS Framework Inference
tensorflow CWE-770 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: ConcatV2 type confusion enables remote DoS

CVE-2022-21731
6.5
EPSS 0.9%
DoS Framework Inference
tensorflow CWE-843 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: OOB read leaks heap memory, enables DoS

CVE-2022-21730
8.1
EPSS 0.8%
Data Extraction DoS Code Execution Framework Inference Training Data
tensorflow CWE-125 3.8K 4 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap OOB read in ReverseSequence op

CVE-2022-21728
8.1
EPSS 1.1%
DoS Data Leakage Framework Inference
tensorflow CWE-125 3.8K 3 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: Dequantize integer overflow, RCE risk

CVE-2022-21727
8.8
EPSS 0.7%
Code Execution DoS Framework Inference
tensorflow CWE-190 3.8K 4 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: heap OOB read in Dequantize op allows RCE

CVE-2022-21726
8.8
EPSS 0.8%
Code Execution Data Extraction Framework Inference
tensorflow CWE-125 3.8K 2 ATLAS
UNKNOWN

InsydeH2O firmware: SMM corruption via NVMe driver bug

CVE-2022-24031
--
EPSS 0.3%
Code Execution Supply Chain Inference
UNKNOWN

InsydeH2O UEFI: unchecked SMM buffer enables SMRAM access

CVE-2021-33625
--
EPSS 0.3%
Code Execution Auth Bypass
UNKNOWN

InsydeH2O UEFI: SMM callout enables ring -2 privesc

CVE-2021-43323
--
EPSS 0.4%
Code Execution Auth Bypass Inference
1 ATLAS
UNKNOWN

InsydeH2O UEFI: SMM callout enables privilege escalation

CVE-2021-42113
--
EPSS 0.3%
Code Execution Inference
UNKNOWN

InsydeH2O UEFI: SMM callout flaw enables ring -2 code exec

CVE-2021-41838
--
EPSS 0.3%
Code Execution Inference
UNKNOWN

InsydeH2O UEFI: SMM memory corruption enables privilege escalation

CVE-2021-42554
--
EPSS 0.3%
Code Execution Supply Chain Inference
UNKNOWN

InsydeH2O UEFI: SMM privilege escalation via NVMe driver bug

CVE-2021-41839
--
EPSS 0.3%
Code Execution Inference
UNKNOWN EXPLOIT AVAIL

InsydeH2O UEFI: SMM buffer flaw enables ring-2 escalation

CVE-2021-33627
--
EPSS 0.3%
Code Execution Inference Training Data

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