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 1961 results — Active exploitation
HIGHEXPLOIT AVAIL

Transformers: ReDoS in Nougat tokenizer causes DoS

CVE-2024-12720
7.5
EPSS 0.7%
DoSFrameworkInference
transformersCWE-13339.8K3 ATLAS
HIGHEXPLOIT AVAIL

llama-index: DoS via infinite loop in LangChain LLM

CVE-2024-12704
7.5
EPSS 0.8%
DoSFramework
llamaindexCWE-7553 ATLAS
MEDIUMEXPLOIT AVAIL

Gradio: NTFS ADS bypass exposes blocked file paths

CVE-2024-12217
5.3
EPSS 0.7%
Data ExtractionData LeakageAuth BypassFrameworkAPI
gradioCWE-227353 ATLAS
UNKNOWNEXPLOIT AVAIL

LLaVA: path traversal allows arbitrary file read

CVE-2024-12065
--
EPSS 0.9%
Data ExtractionData LeakageFrameworkInference
4 ATLAS
HIGHEXPLOIT AVAIL

Ollama: DoS via malicious gguf model file upload

CVE-2024-12055
7.5
EPSS 0.8%
DoSSupply ChainInferenceModelFramework
ollama1.9K4 ATLAS
CRITICALEXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in MessageQueue

CVE-2024-11041
9.8
EPSS 1.7%
Code ExecutionFrameworkInference
vllmCWE-502944 ATLAS
UNKNOWNEXPLOIT AVAIL

gpt_academic: path traversal exposes LLM API keys

CVE-2024-11037
--
EPSS 1.1%
Data ExtractionAuth BypassAPIFramework
gpt_academic5 ATLAS
HIGHEXPLOIT AVAIL

GPT Academic: SSRF in Markdown plugin leaks credentials

CVE-2024-11031
7.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkPlugin
gpt_academic4 ATLAS
HIGHEXPLOIT AVAIL

GPT Academic: SSRF via unsanitized HotReload plugin

CVE-2024-11030
7.5
EPSS 0.7%
Data ExtractionAuth BypassFrameworkPlugin
gpt_academic4 ATLAS
UNKNOWNEXPLOIT AVAIL

gpt_academic: RCE via unsandboxed prompt injection

CVE-2024-10950
--
EPSS 1.5%
Prompt InjectionCode ExecutionFrameworkPlugin
gpt_academic6 ATLAS
MEDIUMEXPLOIT AVAIL

langchain-core: file read via prompt template inputs

CVE-2024-10940
5.3
EPSS 0.4%
Data ExtractionData LeakagePrivacy ViolationFrameworkAgent
langchain-corePatch: 0.1.53CWE-4976.3K4 ATLAS
UNKNOWNEXPLOIT AVAIL

ChuanhuChatGPT: path traversal exposes server files unauthed

CVE-2024-10707
--
EPSS 0.7%
Data ExtractionAuth BypassFrameworkAPI
chuanhuchatgpt3 ATLAS
UNKNOWNEXPLOIT AVAIL

ChuanhuChatGPT: DoS via multipart payload exhaustion

CVE-2024-10650
--
EPSS 0.7%
DoSFrameworkAPI
chuanhuchatgpt3 ATLAS
HIGHEXPLOIT AVAIL

Gradio: path traversal enables arbitrary file deletion DoS

CVE-2024-10648
8.2
EPSS 0.7%
DoSSupply ChainFrameworkInference
gradioCWE-297353 ATLAS
HIGHEXPLOIT AVAIL

Gradio: ReDoS in DateTime causes CPU exhaustion DoS

CVE-2024-10624
7.5
EPSS 1.1%
DoSFrameworkInference
gradioCWE-4007353 ATLAS
HIGHEXPLOIT AVAIL

Gradio: zip bomb DoS via dataframe CSV upload

CVE-2024-10569
7.5
EPSS 0.7%
DoSFramework
gradioCWE-4757353 ATLAS
CRITICALEXPLOIT AVAIL

vLLM: RCE via unsafe deserialization in Mooncake KV

CVE-2025-29783
9.0
EPSS 0.7%
Code ExecutionSupply ChainFrameworkInference
vllmCWE-502945 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: DoS via unbounded grammar cache exhausts disk

CVE-2025-29770
6.5
EPSS 0.5%
DoSInferenceFrameworkAPI
vllmCWE-770944 ATLAS
CRITICALEXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model loading

CVE-2025-1550
9.8
EPSS 2.6%
Code ExecutionSupply ChainFrameworkModel
kerasCWE-944.1K6 ATLAS
LOWEXPLOIT AVAIL

PyTorch: improper init in quantized sigmoid skews model output

CVE-2025-2149
2.5
EPSS 0.3%
Supply ChainAdversarial ExamplesFrameworkInferenceModel
torchCWE-66526.1K3 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