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
2,385

AI/ML CVEs Tracked

340

Critical

390

New This Week

18

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 818 results — Active exploitation, no patch
HIGH EXPLOIT AVAIL

MLflow: CSRF in signup allows rogue account creation

CVE-2025-1473
7.1
EPSS 0.2%
Auth Bypass Data Extraction Framework Training Data
mlflow CWE-352 655 4 ATLAS
HIGH EXPLOIT AVAIL

MLflow: GraphQL DoS disables ML tracking server

CVE-2025-0453
7.5
EPSS 0.5%
DoS Framework
mlflow CWE-400 655 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: DoS via malicious GGUF model file upload

CVE-2025-0317
7.5
EPSS 13.5%
DoS Inference Model
ollama CWE-369 1.6K 4 ATLAS
HIGH EXPLOIT AVAIL

Ollama: GGUF model upload causes memory exhaustion DoS

CVE-2025-0315
7.5
EPSS 0.7%
DoS Inference Model
ollama CWE-770 1.6K 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: null pointer DoS via malicious GGUF model upload

CVE-2025-0312
7.5
EPSS 0.6%
DoS Inference Model Framework
ollama CWE-476 1.6K 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Gradio: DoS via oversized upload filename

CVE-2025-0187
--
EPSS 0.7%
DoS Framework API
gradio 685 3 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via runner deserialization

CVE-2024-9070
9.8
EPSS 0.8%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 21 3 ATLAS
HIGH EXPLOIT AVAIL

BentoML: DoS via multipart boundary exhausts server

CVE-2024-9056
7.5
EPSS 0.7%
DoS Framework Inference
bentoml CWE-400 21 3 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in RPC server

CVE-2024-9053
9.8
EPSS 1.3%
Code Execution Supply Chain Framework Inference
vllm CWE-78 130 5 ATLAS
HIGH EXPLOIT AVAIL

Gradio: DoS via malformed multipart boundary

CVE-2024-8966
7.5
EPSS 0.7%
DoS Framework
video CWE-400 685 3 ATLAS
HIGH EXPLOIT AVAIL

MLflow: path traversal allows arbitrary file read via DBFS

CVE-2024-8859
7.5
EPSS 2.5%
Data Extraction Data Leakage Framework Training Data
mlflow CWE-22 655 5 ATLAS
HIGH EXPLOIT AVAIL

ollama: divide-by-zero DoS via crafted GGUF model import

CVE-2024-8063
7.5
EPSS 0.6%
DoS Supply Chain Inference Model Framework
ollama 1.6K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Gradio: open redirect exposes AI demo users to phishing

CVE-2024-8021
6.1
EPSS 0.7%
Social Engineering Auth Bypass Framework API
gradio CWE-601 685 4 ATLAS
HIGH EXPLOIT AVAIL

Open-WebUI: SSRF via unchecked OpenAI URL leaks internal secrets

CVE-2024-7959
7.7
EPSS 24.5%
Data Extraction Auth Bypass Code Execution API Framework
open-webui CWE-918 5 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: unconstrained input causes UI denial of service

CVE-2024-6838
5.3
EPSS 0.6%
DoS Framework
mlflow CWE-400 655 3 ATLAS
MEDIUM EXPLOIT AVAIL

TorchServe: unverified S3 bucket exposes benchmark data

CVE-2024-6577
6.3
EPSS 0.4%
Supply Chain Data Leakage Data Extraction Framework Inference
torchserve 22.7K 3 ATLAS
HIGH EXPLOIT AVAIL

llama-index: SQLi+DoS via prompt injection in query engine

CVE-2024-12911
7.1
EPSS 0.5%
Prompt Injection Code Execution DoS Framework Agent
llamaindex CWE-89 6 ATLAS
UNKNOWN EXPLOIT AVAIL

Dify: SSRF via custom tool URL enables credential theft

CVE-2024-12775
--
EPSS 0.6%
Data Extraction Auth Bypass Framework API Agent
5 ATLAS
HIGH EXPLOIT AVAIL

Transformers: ReDoS in Nougat tokenizer causes DoS

CVE-2024-12720
7.5
EPSS 0.7%
DoS Framework Inference
transformers CWE-1333 8.3K 3 ATLAS
HIGH EXPLOIT AVAIL

llama-index: DoS via infinite loop in LangChain LLM

CVE-2024-12704
7.5
EPSS 0.8%
DoS Framework
llamaindex CWE-755 3 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