AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

76

New This Week

16

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 1604 results
Severity CVE ID Summary CVSS EPSS Package Date
UNKN E CVE-2024-10650 ChuanhuChatGPT: DoS via multipart payload exhaustion — 0.7% chuanhuchatgpt Mar 20 HIGH E CVE-2024-10648 Gradio: path traversal enables arbitrary file deletion DoS 8.2 0.3% gradio Mar 20 HIGH E CVE-2024-10624 Gradio: ReDoS in DateTime causes CPU exhaustion DoS 7.5 0.8% gradio Mar 20 HIGH E CVE-2024-10569 Gradio: zip bomb DoS via dataframe CSV upload 7.5 0.5% gradio Mar 20 HIGH CVE-2024-10188 litellm: unauthenticated DoS crashes LLM proxy server 7.5 0.3% litellm Mar 20 CRIT E CVE-2025-29783 vLLM: RCE via unsafe deserialization in Mooncake KV 9.0 2.8% vllm Mar 19 MEDI E CVE-2025-29770 vLLM: DoS via unbounded grammar cache exhausts disk 6.5 0.7% vllm Mar 19 CRIT E CVE-2025-1550 Keras: safe_mode bypass enables RCE via model loading 9.8 8.0% keras Mar 11 LOW E CVE-2025-2149 PyTorch: improper init in quantized sigmoid skews model output 2.5 0.1% pytorch Mar 10 HIGH E CVE-2025-2148 PyTorch: memory corruption in JIT profiler callback handler 7.5 0.1% pytorch Mar 10 CRIT E CVE-2025-1945 picklescan: ZIP flag bypass enables RCE in PyTorch models 9.8 0.9% picklescan Mar 10 MEDI E CVE-2025-1944 picklescan: ZIP spoof lets malicious PyTorch models bypass scan 6.5 0.1% picklescan Mar 10 MEDI CVE-2025-1979 Ray: Redis password exposed via plaintext logging 6.4 0.1% ray Mar 6 CRIT E CVE-2025-25362 spacy-llm: SSTI allows unauthenticated RCE (CVSS 9.8) 9.8 0.0% spacy-llm Mar 5 LOW CVE-2025-1953 vLLM AIBrix: weak hash in prefix cache leaks inference patterns 2.6 0.1% — Mar 4 MEDI E CVE-2025-1716 picklescan: scanner bypass enables supply chain RCE — 16.2% picklescan Mar 3 MEDI E CVE-2025-1889 picklescan: extension bypass enables RCE on model load — 0.1% picklescan Mar 3 HIGH E CVE-2025-25185 gpt_academic: symlink traversal exposes all server files 7.5 0.6% gpt_academic Mar 3 CRIT CVE-2023-25574 JupyterHub LTI13: JWT forgery enables full auth bypass 10.0 0.4% — Feb 25 HIGH CVE-2025-25297 Label Studio: SSRF via S3 endpoint exposes internal services 8.6 0.1% label-studio Feb 14

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