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
3,591

AI/ML CVEs Tracked

481

Critical

84

New This Week

24

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 2346 results — no patch
HIGH EXPLOIT AVAIL

Gradio: zip bomb DoS via dataframe CSV upload

CVE-2024-10569
7.5
EPSS 0.6%
DoS Framework
gradio CWE-475 721 3 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via unsafe deserialization in Mooncake KV

CVE-2025-29783
9.0
EPSS 0.7%
Code Execution Supply Chain Framework Inference
vllm CWE-502 92 5 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: DoS via unbounded grammar cache exhausts disk

CVE-2025-29770
6.5
EPSS 0.5%
DoS Inference Framework API
vllm CWE-770 92 4 ATLAS
CRITICAL EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model loading

CVE-2025-1550
9.8
EPSS 2.6%
Code Execution Supply Chain Framework Model
keras CWE-94 1.5K 6 ATLAS
LOW EXPLOIT AVAIL

PyTorch: improper init in quantized sigmoid skews model output

CVE-2025-2149
2.5
EPSS 0.3%
Supply Chain Adversarial Examples Framework Inference Model
torch CWE-665 25.2K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: memory corruption in JIT profiler callback handler

CVE-2025-2148
7.5
EPSS 0.4%
Code Execution Supply Chain Framework Inference
torch CWE-119 25.2K 3 ATLAS
CRITICAL EXPLOIT AVAIL

picklescan: ZIP flag bypass enables RCE in PyTorch models

CVE-2025-1945
9.8
EPSS 0.6%
Supply Chain Code Execution Model Framework
picklescan CWE-345 3 6 ATLAS
CRITICAL

B2B Login Panel: SQLi enables unauthenticated DB access

CVE-2024-13147
9.8
EPSS 0.4%
Auth Bypass Data Extraction Framework API
B2B Login Panel 505 4 ATLAS
LOW

vLLM AIBrix: weak hash in prefix cache leaks inference patterns

CVE-2025-1953
2.6
EPSS 0.3%
Data Leakage Privacy Violation Inference Framework
3 ATLAS
HIGH EXPLOIT AVAIL

gpt_academic: symlink traversal exposes all server files

CVE-2025-25185
7.5
EPSS 0.6%
Data Extraction Privacy Violation Framework
gpt_academic 4 ATLAS
CRITICAL

Mobuy Panel: SQLi allows unauthenticated DB takeover

CVE-2024-13152
10.0
EPSS 0.5%
Data Extraction Auth Bypass Code Execution Framework
Mobuy Online Machinery Monitoring Panel 505 4 ATLAS
CRITICAL

PandasAI: prompt injection enables unauthenticated RCE

CVE-2024-12366
9.8
EPSS 1.2%
Prompt Injection Code Execution Framework Agent
CWE-94 6 ATLAS
MEDIUM EXPLOIT AVAIL

serialize-javascript: XSS via regex in AI/ML dashboards

CVE-2024-11831
5.4
EPSS 1.1%
Supply Chain Code Execution Data Extraction Framework Plugin
odh-kf-notebook-controller-rhel8 3.1K 4 ATLAS
LOW

vLLM: hash collision enables prefix cache poisoning

CVE-2025-25183
2.6
EPSS 0.2%
Adversarial Examples Data Leakage Inference Framework
vllm CWE-354 92 5 ATLAS
HIGH

vLLM: unsafe deserialization RCE via model loading

CVE-2025-24357
8.8
EPSS 0.7%
Supply Chain Code Execution Framework Inference Model
vllm CWE-502 92 5 ATLAS
MEDIUM

Jobify WP: missing authz allows OpenAI key abuse, SSRF

CVE-2024-13698
6.5
EPSS 0.3%
Auth Bypass DoS Data Extraction API Plugin
5 ATLAS
HIGH

nbgrader: Clickjacking exposes formgrader via IFrame

CVE-2025-23205
--
EPSS 0.5%
Data Extraction Social Engineering Auth Bypass Framework
CWE-668 4 ATLAS
HIGH EXPLOIT AVAIL

Gradio: ACL bypass via path case manipulation

CVE-2025-23042
7.5
EPSS 1.0%
Auth Bypass Data Extraction Framework API
gradio CWE-178 721 4 ATLAS
MEDIUM EXPLOIT AVAIL

Keras: path traversal enables arbitrary file write

CVE-2024-55459
6.5
EPSS 0.2%
Supply Chain Code Execution Framework Training Data
keras CWE-22 1.5K 4 ATLAS
UNKNOWN

AIDeepin: MD5 collision enables RAG knowledge base poisoning

CVE-2025-21604
--
EPSS 0.3%
Supply Chain Model Poisoning RAG Framework
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