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

95

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
CRITICALEXPLOIT AVAIL

BentoML: unauthenticated RCE via insecure deserialization

CVE-2025-27520
9.8
EPSS 40.6%
Code ExecutionSupply ChainFrameworkInference
bentomlCWE-502235 ATLAS
HIGHEXPLOIT AVAIL

jupyterlab-git: command injection via malicious repo name

CVE-2025-30370
7.4
EPSS 0.6%
Code ExecutionSupply ChainFrameworkPlugin
jupyterlab-gitPatch: 0.51.1CWE-781.9K4 ATLAS
LOWEXPLOIT AVAIL

PyTorch: memory corruption in CUDA caching allocator

CVE-2025-3136
3.3
EPSS 0.3%
DoSFrameworkInference
pytorchCWE-78726.1K2 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: memory corruption in JIT flatbuffer loader

CVE-2025-3121
5.5
EPSS 0.3%
DoSSupply ChainFrameworkInference
pytorch26.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: lstm_cell memory corruption, local code exec

CVE-2025-3001
5.3
EPSS 0.2%
Code ExecutionDoSFramework
torchPatch: 2.10.0CWE-11926.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: memory corruption in torch.jit.script compiler

CVE-2025-3000
5.3
EPSS 0.2%
Code ExecutionSupply ChainFrameworkInference
torchPatch: 2.13.0CWE-11926.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: memory corruption in RNN sequence unpacking

CVE-2025-2999
5.3
EPSS 0.2%
Code ExecutionData ExtractionSupply ChainFrameworkTraining DataInference
torchPatch: 2.9.1CWE-11926.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: memory corruption in RNN pad_packed_sequence

CVE-2025-2998
5.3
EPSS 0.2%
Code ExecutionSupply ChainDoSFrameworkTraining Data
torchCWE-11926.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: DoS via mkldnn_max_pool2d resource leak

CVE-2025-2953
5.5
EPSS 0.3%
DoSSupply ChainFrameworkInferenceModel
pytorchCWE-40426.1K3 ATLAS
MEDIUMEXPLOIT AVAIL

openairinterface5g: segfault enables DoS via crafted UE message

CVE-2025-26265
6.5
EPSS 0.5%
DoSInference
openairinterface5g15.6K2 ATLAS
CRITICALEXPLOIT AVAIL

InvokeAI: RCE via unsafe torch.load deserialization

CVE-2024-12029
9.8
EPSS 6.0%
Code ExecutionSupply ChainFrameworkModel
InvokeAIPatch: 5.4.3rc2CWE-5025 ATLAS
HIGHEXPLOIT AVAIL

LiteLLM: Langfuse API key leak via error handling

CVE-2025-0330
7.5
EPSS 0.6%
Data LeakageAuth BypassData ExtractionFrameworkAPIInference
litellmCWE-123064 ATLAS
HIGHEXPLOIT AVAIL

litellm: privilege escalation viewer→proxy admin via bad API key

CVE-2025-0628
8.1
EPSS 0.3%
Auth BypassData ExtractionAPIFramework
litellmPatch: 1.61.15CWE-26664 ATLAS
MEDIUMEXPLOIT AVAIL

SageMaker SDK: MD5 collision silently replaces ML workflows

CVE-2025-0508
5.9
EPSS 0.3%
Supply ChainModel PoisoningFrameworkTraining Data
sagemakerPatch: 2.237.3CWE-328503 ATLAS
HIGHEXPLOIT AVAIL

litellm: unauthenticated DoS via multipart boundary parsing

CVE-2024-8984
7.5
EPSS 0.9%
DoSAPIFrameworkInference
litellmPatch: 1.56.2CWE-40063 ATLAS
HIGHEXPLOIT AVAIL

pytorch-lightning: unauthenticated DoS crashes LightningApp

CVE-2024-8020
7.5
EPSS 0.6%
DoSFrameworkAPI
pytorch-lightningCWE-2481.7K3 ATLAS
HIGHEXPLOIT AVAIL

open-webui: Stored XSS enables admin session hijack

CVE-2024-7990
8.4
EPSS 0.9%
Code ExecutionData ExtractionAuth BypassFrameworkAPI
open-webuiCWE-7923 ATLAS
HIGHEXPLOIT AVAIL

OpenWebUI: path traversal RCE via audio upload API

CVE-2024-8060
8.1
EPSS 0.9%
Code ExecutionData ExtractionFrameworkAPI
open-webuiPatch: 0.5.17CWE-2225 ATLAS
HIGHEXPLOIT AVAIL

Open-WebUI: unauthenticated PDF endpoint enables DoS

CVE-2024-8053
7.5
EPSS 0.7%
Auth BypassDoSAPIInference
open-webuiCWE-28723 ATLAS
HIGHEXPLOIT AVAIL

open-webui: unauthenticated DoS via markdown parser

CVE-2024-7983
7.5
EPSS 0.9%
DoSAuth BypassAPIFramework
open-webuiCWE-40023 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