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 4307 results
HIGHEXPLOIT AVAIL

Gradio: unauthenticated file copy enables disk DoS

CVE-2025-48889
7.5
EPSS 0.7%
DoSFrameworkInference
gradioCWE-4347353 ATLAS
HIGH

vLLM: image hash collision enables multimodal cache leakage

CVE-2025-46722
7.3
EPSS 0.3%
Data LeakagePrivacy ViolationInferenceFramework
vllmCWE-1023944 ATLAS
LOW

vLLM: timing side-channel leaks prompt cache data

CVE-2025-46570
2.6
EPSS 0.4%
Privacy ViolationData ExtractionInferenceFramework
vllmCWE-203944 ATLAS
LOWEXPLOIT AVAIL

Gradio: CORS origin bypass in ML UI handler

CVE-2025-5320
3.7
EPSS 0.3%
Auth BypassFrameworkInference
gradioCWE-3457353 ATLAS
MEDIUM

vllm: ReDoS in inference endpoints enables DoS

GHSA-j828-28rj-hfhp
4.3
DoSInferenceFramework
vllmPatch: 0.9.0CWE-1333943 ATLAS
HIGHEXPLOIT AVAIL

llama-index-cli: OS command injection enables RCE

CVE-2025-1753
7.8
EPSS 1.1%
Code ExecutionSupply ChainFrameworkAgent
llama-indexCWE-782514 ATLAS
MEDIUM

GNU Coreutils sort: heap under-read in begfield()

CVE-2025-5278
4.4
Data LeakageDoSFrameworkInference
rhoai/odh-llama-stack-k8s-operator-rhel9141 ATLAS
HIGH

label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader

CVE-2025-5173
7.8
EPSS 0.2%
Supply ChainCode ExecutionFrameworkModel
label-studio-mlCWE-50224 ATLAS
CRITICALEXPLOIT AVAIL

vLLM: RCE via exposed TCPStore in distributed inference

CVE-2025-47277
9.8
EPSS 1.0%
Code ExecutionData ExtractionInferenceFramework
vllmCWE-502944 ATLAS
HIGHEXPLOIT AVAIL

transformers: ReDoS in testing_utils causes DoS

CVE-2025-2099
7.5
EPSS 0.6%
DoSFramework
transformersCWE-13339.8K3 ATLAS
UNKNOWNEXPLOIT AVAIL

Ollama: DoS via malicious manifest in /api/pull

CVE-2025-1975
--
EPSS 0.5%
DoSInferenceAPI
ollama1.9K3 ATLAS
HIGHEXPLOIT AVAIL

Label Studio: XSS enables unauthorized actions via CSRF

CVE-2025-47783
--
EPSS 0.6%
Code ExecutionData LeakageSocial EngineeringFrameworkTraining Data
label-studioPatch: 1.18.0CWE-7925 ATLAS
HIGHEXPLOIT AVAIL

llama_index: DoS via uncapped recursion in web reader

CVE-2025-1752
7.5
EPSS 0.5%
DoSFrameworkRAG
llama-indexPatch: 0.12.21CWE-4002513 ATLAS
HIGH

TensorFlow Serving: JSON recursion DoS on inference API

CVE-2025-0649
7.5
EPSS 0.2%
DoSInferenceAPIFramework
tensorflow_servingCWE-7873.4K3 ATLAS
HIGH

vLLM: pickle RCE in multi-node inference deployments

CVE-2025-30165
8.0
EPSS 0.6%
Code ExecutionInferenceFramework
vllmCWE-502943 ATLAS
LOWEXPLOIT AVAIL

PyTorch NCCL: local DoS in distributed training reduce op

CVE-2025-4287
3.3
EPSS 0.2%
DoSFrameworkTraining Data
3 ATLAS
CRITICALEXPLOIT AVAIL

browser-use: URL allowlist bypass enables SSRF in agents

CVE-2025-47241
9.3
EPSS 0.5%
Auth BypassData ExtractionAgentFramework
browser-usePatch: 0.1.45CWE-647755 ATLAS
HIGHEXPLOIT AVAIL

LLaMA-Factory: RCE via torch.load() unsafe deserialization

CVE-2025-46567
7.8
EPSS 0.3%
Code ExecutionSupply ChainFrameworkTraining Data
llamafactoryPatch: 0.9.3CWE-50235 ATLAS
HIGHEXPLOIT AVAIL

vLLM: DoS via quadratic multimodal tokenizer input

CVE-2025-46560
7.5
EPSS 0.5%
DoSInferenceFramework
vllmCWE-1333943 ATLAS
CRITICALEXPLOIT AVAIL

vLLM: RCE via pickle deserialization on ZeroMQ

CVE-2025-32444
9.8
EPSS 1.8%
Code ExecutionSupply ChainInferenceFramework
vllmCWE-502945 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