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
2,377

AI/ML CVEs Tracked

337

Critical

392

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 314 results — Medium severity, Active exploitation
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in torch.jit.script compiler

CVE-2025-3000
5.3
EPSS 0.2%
Code Execution Supply Chain Framework Inference
torch CWE-119 22.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in RNN sequence unpacking

CVE-2025-2999
5.3
EPSS 0.2%
Code Execution Data Extraction Supply Chain Framework Training Data Inference
torch Patch: 2.9.1 CWE-119 22.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in RNN pad_packed_sequence

CVE-2025-2998
5.3
EPSS 0.2%
Code Execution Supply Chain DoS Framework Training Data
torch CWE-119 22.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: DoS via mkldnn_max_pool2d resource leak

CVE-2025-2953
5.5
EPSS 0.2%
DoS Supply Chain Framework Inference Model
pytorch CWE-404 22.7K 3 ATLAS
MEDIUM EXPLOIT AVAIL

openairinterface5g: segfault enables DoS via crafted UE message

CVE-2025-26265
6.5
EPSS 0.4%
DoS Inference
openairinterface5g 16.6K 2 ATLAS
MEDIUM EXPLOIT AVAIL

SageMaker SDK: MD5 collision silently replaces ML workflows

CVE-2025-0508
5.9
EPSS 0.2%
Supply Chain Model Poisoning Framework Training Data
sagemaker Patch: 2.237.3 CWE-328 51 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: missing authz leaks admin credentials

CVE-2024-7046
4.3
EPSS 0.4%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui CWE-475 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: missing authz exposes admin prompts

CVE-2024-7045
4.3
EPSS 0.4%
Auth Bypass Data Leakage API Framework
open-webui CWE-862 5 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: CSRF wipes RAG DB and AI memories via GET

CVE-2024-7035
6.9
EPSS 0.2%
DoS Auth Bypass RAG API Framework
open-webui CWE-352 5 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: path traversal allows arbitrary file write/RCE

CVE-2024-7034
6.5
EPSS 2.5%
Code Execution Supply Chain Framework Inference API
open-webui CWE-22 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: path traversal allows file write and RCE

CVE-2024-7033
6.5
EPSS 1.1%
Code Execution DoS Framework Inference
open-webui CWE-29 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: Stored XSS via file upload, session hijack

CVE-2024-7044
6.8
EPSS 0.5%
Auth Bypass Data Extraction Social Engineering Framework API
open-webui CWE-79 5 ATLAS
MEDIUM EXPLOIT AVAIL

llama-index: DoS via infinite recursion in web reader

CVE-2024-12910
5.9
EPSS 0.6%
DoS Supply Chain Framework RAG
llama-index Patch: 0.12.9 CWE-400 238 4 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: passwordless accounts enable persistent backdoor

CVE-2025-1474
5.5
EPSS 0.3%
Auth Bypass Supply Chain Model Poisoning Framework Training Data Model
mlflow CWE-521 655 5 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
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
MEDIUM EXPLOIT AVAIL

Gradio: NTFS ADS bypass exposes blocked file paths

CVE-2024-12217
5.3
EPSS 0.6%
Data Extraction Data Leakage Auth Bypass Framework API
gradio CWE-22 685 3 ATLAS
MEDIUM EXPLOIT AVAIL

langchain-core: file read via prompt template inputs

CVE-2024-10940
5.3
EPSS 0.4%
Data Extraction Data Leakage Privacy Violation Framework Agent
langchain-core Patch: 0.1.53 CWE-497 4.8K 4 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: DoS via unbounded grammar cache exhausts disk

CVE-2025-29770
6.5
EPSS 0.4%
DoS Inference Framework API
vllm CWE-770 130 4 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