AI Threat AlertAI 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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 1961 results — Active exploitationCVE-2024-12720Transformers: ReDoS in Nougat tokenizer causes DoS7.50.7%transformersMar 20HIGHECVE-2024-12704llama-index: DoS via infinite loop in LangChain LLM7.50.8%llamaindexMar 20MEDIECVE-2024-12217Gradio: NTFS ADS bypass exposes blocked file paths5.30.7%gradioMar 20UNKNECVE-2024-12065LLaVA: path traversal allows arbitrary file read—0.9%—Mar 20HIGHECVE-2024-12055Ollama: DoS via malicious gguf model file upload7.50.8%ollamaMar 20CRITECVE-2024-11041vllm: RCE via unsafe pickle deserialization in MessageQueue9.81.7%vllmMar 20UNKNECVE-2024-11037gpt_academic: path traversal exposes LLM API keys—1.1%gpt_academicMar 20HIGHECVE-2024-11031GPT Academic: SSRF in Markdown plugin leaks credentials7.50.7%gpt_academicMar 20HIGHECVE-2024-11030GPT Academic: SSRF via unsanitized HotReload plugin7.50.7%gpt_academicMar 20UNKNECVE-2024-10950gpt_academic: RCE via unsandboxed prompt injection—1.5%gpt_academicMar 20MEDIECVE-2024-10940langchain-core: file read via prompt template inputs5.30.4%langchain-coreMar 20UNKNECVE-2024-10707ChuanhuChatGPT: path traversal exposes server files unauthed—0.7%chuanhuchatgptMar 20UNKNECVE-2024-10650ChuanhuChatGPT: DoS via multipart payload exhaustion—0.7%chuanhuchatgptMar 20HIGHECVE-2024-10648Gradio: path traversal enables arbitrary file deletion DoS8.20.7%gradioMar 20HIGHECVE-2024-10624Gradio: ReDoS in DateTime causes CPU exhaustion DoS7.51.1%gradioMar 20HIGHECVE-2024-10569Gradio: zip bomb DoS via dataframe CSV upload7.50.7%gradioMar 20CRITECVE-2025-29783vLLM: RCE via unsafe deserialization in Mooncake KV9.00.7%vllmMar 19MEDIECVE-2025-29770vLLM: DoS via unbounded grammar cache exhausts disk6.50.5%vllmMar 19CRITECVE-2025-1550Keras: safe_mode bypass enables RCE via model loading9.82.6%kerasMar 11LOWECVE-2025-2149PyTorch: improper init in quantized sigmoid skews model output2.50.3%torchMar 10Frequently 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