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

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
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
HIGHEXPLOIT AVAIL

vLLM: ZeroMQ socket exposure enables DoS in multi-node

CVE-2025-30202
7.5
EPSS 0.6%
DoSData LeakageInferenceFramework
vllmCWE-770944 ATLAS
MEDIUMEXPLOIT AVAIL

transformers: ReDoS in GPT-NeoX Japanese tokenizer

CVE-2025-1194
6.5
EPSS 0.5%
DoSFramework
transformersCWE-13339.8K4 ATLAS
CRITICALEXPLOIT AVAIL

PHPGurukul: session hijack via password change flow

CVE-2025-45949
9.8
EPSS 0.5%
Auth BypassFramework
CRITICALEXPLOIT AVAIL

PHPGurukul Hostel Mgmt: session hijacking → takeover

CVE-2025-45953
9.1
EPSS 0.4%
Auth Bypass
CRITICALEXPLOIT AVAIL

PyTorch: RCE bypasses weights_only=True safe-load guard

CVE-2025-32434
9.8
EPSS 2.4%
Code ExecutionSupply ChainFrameworkModelInference
pytorchCWE-50226.1K6 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: DoS via ctc_loss resource mishandling

CVE-2025-3730
5.5
EPSS 0.3%
DoSFramework
pytorchCWE-40426.1K3 ATLAS
CRITICALEXPLOIT AVAIL

jupyter-remote-desktop-proxy: VNC network exposure

CVE-2025-32428
--
EPSS 0.9%
Auth BypassData LeakagePrivacy ViolationFramework
jupyter-remote-desktop-proxyPatch: 3.0.1CWE-6681.9K5 ATLAS
CRITICALEXPLOIT AVAIL

BentoML: RCE via insecure deserialization in runner

CVE-2025-32375
9.8
EPSS 52.4%
Code ExecutionData ExtractionSupply ChainFrameworkInference
bentomlCWE-502235 ATLAS
HIGHEXPLOIT AVAIL

picklescan: scanner bypass enables DNS data exfiltration

CVE-2025-46417
--
EPSS 0.2%
Supply ChainData ExtractionData LeakageFrameworkModel
picklescanPatch: 0.0.25CWE-18436 ATLAS
CRITICALKEVSCANNER

Langflow: Unauth RCE via code injection endpoint

CVE-2025-3248
9.8
EPSS 100.0%
Code ExecutionAuth BypassFrameworkAgent
langflowCWE-945 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