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

337

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
CRITICAL EXPLOIT AVAIL

vLLM: RCE via exposed TCPStore in distributed inference

CVE-2025-47277
9.8
EPSS 0.9%
Code Execution Data Extraction Inference Framework
vllm CWE-502 130 4 ATLAS
HIGH EXPLOIT AVAIL

transformers: ReDoS in testing_utils causes DoS

CVE-2025-2099
7.5
EPSS 0.5%
DoS Framework
transformers CWE-1333 8.3K 3 ATLAS
UNKNOWN EXPLOIT AVAIL

Ollama: DoS via malicious manifest in /api/pull

CVE-2025-1975
--
EPSS 0.4%
DoS Inference API
ollama 1.6K 3 ATLAS
LOW EXPLOIT AVAIL

PyTorch NCCL: local DoS in distributed training reduce op

CVE-2025-4287
3.3
EPSS 0.1%
DoS Framework Training Data
3 ATLAS
HIGH EXPLOIT AVAIL

vLLM: DoS via quadratic multimodal tokenizer input

CVE-2025-46560
7.5
EPSS 0.4%
DoS Inference Framework
vllm CWE-1333 130 3 ATLAS
CRITICAL EXPLOIT AVAIL

vLLM: RCE via pickle deserialization on ZeroMQ

CVE-2025-32444
9.8
EPSS 1.5%
Code Execution Supply Chain Inference Framework
vllm CWE-502 130 5 ATLAS
HIGH EXPLOIT AVAIL

vLLM: ZeroMQ socket exposure enables DoS in multi-node

CVE-2025-30202
7.5
EPSS 0.5%
DoS Data Leakage Inference Framework
vllm CWE-770 130 4 ATLAS
MEDIUM EXPLOIT AVAIL

transformers: ReDoS in GPT-NeoX Japanese tokenizer

CVE-2025-1194
6.5
EPSS 0.4%
DoS Framework
transformers CWE-1333 8.3K 4 ATLAS
CRITICAL EXPLOIT AVAIL

PyTorch: RCE bypasses weights_only=True safe-load guard

CVE-2025-32434
9.8
EPSS 1.9%
Code Execution Supply Chain Framework Model Inference
pytorch CWE-502 22.7K 6 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: DoS via ctc_loss resource mishandling

CVE-2025-3730
5.5
EPSS 0.3%
DoS Framework
pytorch CWE-404 22.7K 3 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization in runner

CVE-2025-32375
9.8
EPSS 43.8%
Code Execution Data Extraction Supply Chain Framework Inference
bentoml CWE-502 21 5 ATLAS
CRITICAL KEV SCANNER

Langflow: Unauth RCE via code injection endpoint

CVE-2025-3248
9.8
EPSS 100.0%
Code Execution Auth Bypass Framework Agent
langflow CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via insecure deserialization

CVE-2025-27520
9.8
EPSS 43.7%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 21 5 ATLAS
LOW EXPLOIT AVAIL

PyTorch: memory corruption in CUDA caching allocator

CVE-2025-3136
3.3
EPSS 0.2%
DoS Framework Inference
pytorch CWE-787 22.7K 2 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in JIT flatbuffer loader

CVE-2025-3121
5.5
EPSS 0.2%
DoS Supply Chain Framework Inference
pytorch 22.7K 3 ATLAS
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 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
HIGH EXPLOIT AVAIL

LiteLLM: Langfuse API key leak via error handling

CVE-2025-0330
7.5
EPSS 0.5%
Data Leakage Auth Bypass Data Extraction Framework API Inference
litellm CWE-1230 6 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