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
CRITICALEXPLOIT AVAIL

HuggingFace Transformers: RCE via pickle deserialization

CVE-2024-3568
9.6
EPSS 2.1%
Code ExecutionSupply ChainFrameworkModel
transformers9.8K5 ATLAS
HIGHEXPLOIT AVAILSCANNER

Gradio: path traversal leaks arbitrary files, potential RCE

CVE-2024-1728
7.5
EPSS 85.4%
Data ExtractionCode ExecutionPrivacy ViolationFrameworkAPIInference
gradio7356 ATLAS
MEDIUMEXPLOIT AVAIL

Ollama: DNS rebinding exposes LLM API to remote access

CVE-2024-28224
6.6
EPSS 0.4%
Auth BypassDoSData ExtractionInferenceAPIModel
ollama1.9K4 ATLAS
CRITICALEXPLOIT AVAIL

gpt_academic: deserialization RCE, no auth required

CVE-2024-31224
9.8
EPSS 1.2%
Code ExecutionData ExtractionFrameworkAPI
gpt_academic5 ATLAS
UNKNOWNEXPLOIT AVAIL

Gradio: timing attack enables auth bypass on ML UIs

CVE-2024-1729
--
EPSS 0.5%
Auth BypassFrameworkInference
gradio7354 ATLAS
HIGHEXPLOIT AVAIL

Gradio: CI/CD command injection enables secrets exfil

CVE-2024-1540
8.2
EPSS 2.0%
Code ExecutionSupply ChainFramework
gradio7354 ATLAS
MEDIUMEXPLOIT AVAIL

Vert.x: memory leak in HTTP client enables DoS

CVE-2024-1023
6.5
EPSS 1.7%
MEDIUMEXPLOIT AVAIL

Gradio: SSRF exposes internal HuggingFace endpoints

CVE-2024-2206
6.5
EPSS 0.4%
Data ExtractionAuth BypassFrameworkInferenceAPI
gradio7354 ATLAS
MEDIUMEXPLOIT AVAIL

LangChain: Billion Laughs XML expansion causes DoS

CVE-2024-1455
5.9
EPSS 0.8%
DoSFramework
langchain3.2K4 ATLAS
UNKNOWNEXPLOIT AVAIL

Gradio: CSRF enables disk exhaustion via file upload DoS

CVE-2024-1727
--
EPSS 0.4%
DoSAuth BypassFramework
gradio7353 ATLAS
HIGHEXPLOIT AVAIL

LangChain: path traversal enables RCE and API key theft

CVE-2024-28088
8.1
EPSS 1.7%
Code ExecutionData LeakageSupply ChainFrameworkAgentAPI
langchainCWE-223.2K6 ATLAS
CRITICALEXPLOIT AVAIL

LangChain TFIDFRetriever: SSRF/RCE via load_local

CVE-2024-2057
9.8
EPSS 0.6%
Code ExecutionData ExtractionFrameworkRAG
langchain3.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain Experimental: RCE via Python sandbox escape

CVE-2024-27444
9.8
EPSS 0.8%
Code ExecutionSupply ChainFrameworkAgent
langchain-experimental3.2K4 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: XSS in recipe runner enables Jupyter RCE

CVE-2024-27133
9.6
EPSS 0.7%
Code ExecutionSupply ChainFramework
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: XSS in recipes enables client-side RCE

CVE-2024-27132
9.6
EPSS 0.9%
Code ExecutionSupply ChainData ExtractionFrameworkTraining Data
mlflow6955 ATLAS
MEDIUM

Intel TF Opt: buffer overflow enables local privesc

CVE-2023-30767
6.7
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
optimization_for_tensorflowCWE-1193.4K3 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: unauthenticated LFI exposes full server filesystem

CVE-2024-0964
9.4
EPSS 1.0%
Data ExtractionData LeakageAuth BypassFrameworkInferenceAPI
gradioCWE-227355 ATLAS
CRITICALEXPLOIT AVAIL

Nginx-UI: arbitrary file write via cert import leads to RCE

CVE-2024-23827
9.8
EPSS 0.7%
Code ExecutionAPI
github.com/0xJacky/Nginx-UIPatch: 1.9.10-0.20240128060047-8581bdd3c6f4CWE-221.8K2 ATLAS
HIGHEXPLOIT AVAIL

libtiff: heap overflow DoS in vLLM inference via TIFF input

CVE-2023-52356
7.5
EPSS 2.5%
DoSInference
rhaiis/vllm-cuda-rhel9943 ATLAS
HIGHEXPLOIT AVAIL

libtiff: OOM DoS in vLLM inference container images

CVE-2023-52355
7.5
EPSS 1.8%
DoSInference
rhaiis/vllm-cuda-rhel9942 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