AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 15 of 435 results — High severity, Active exploitationTensorFlow: heap buffer overflow in RaggedBincount op
CVE-2021-29514 TensorFlow: type confusion → null ptr deref (CVSS 7.8)
CVE-2021-29513 TensorFlow: heap buffer overflow in RaggedBincount op
CVE-2021-29512 TensorFlow: OOB read in glob path matching causes DoS
CVE-2020-26269 TensorFlow: OOB read in DataFormatVecPermute op
CVE-2020-26267 scikit-learn: DoS via crafted SVM model deserialization
CVE-2020-28975 TensorFlow: NaN-triggered DoS in crop_and_resize op
CVE-2020-15266 TensorFlow: OOB read DoS via invalid quantize axis
CVE-2020-15265 TensorFlow Lite: OOB write in segment sum, memory corruption risk
CVE-2020-15214 TensorFlow Lite: heap OOB write via segment sum op
CVE-2020-15212 TensorFlow: SavedModel protobuf DoS in inference serving
CVE-2020-15206 TensorFlow: format string DoS in strings.as_string
CVE-2020-15203 TensorFlow: heap overflow in sparse gradient op
CVE-2020-15195 TensorFlow: uninitialized memory corruption via dlpack
CVE-2020-15193 TensorFlow: type confusion DoS crashes eager mode inference
CVE-2020-5215 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
AI Threat Alert