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 20 of 766 results — Active exploitation, no patchTensorFlow: null-ptr deref in eager mode causes DoS
CVE-2022-29207 TensorFlow: LSTMBlockCell DoS via invalid tensor rank
CVE-2022-29200 TensorFlow: CHECK-fail DoS in LoadAndRemapMatrix op
CVE-2022-29199 TensorFlow: DoS via sparse tensor input validation failure
CVE-2022-29198 TensorFlow: DoS via UnsortedSegmentJoin input validation
CVE-2022-29197 TensorFlow: DoS via invalid Conv3D filter input
CVE-2022-29196 TensorFlow: StagePeek DoS via unvalidated index scalar
CVE-2022-29195 TensorFlow: DoS via TensorSummaryV2 input validation failure
CVE-2022-29193 TensorFlow: DoS via malformed DeleteSessionTensor input
CVE-2022-29194 TensorFlow: DoS via QuantizeAndDequantize input validation
CVE-2022-29192 TensorFlow: DoS via GetSessionTensor input validation
CVE-2022-29191 Gradio: CSV formula injection via flagging enables RCE
CVE-2022-24770 pytorch-lightning: code injection enables full RCE
CVE-2022-0845 MLflow: insecure temp file handling causes DoS
CVE-2022-0736 TensorFlow XLA: null pointer dereference causes DoS
CVE-2022-23595 TensorFlow MLIR-TFRT: DoS via scalar shape segfault
CVE-2022-23593 TensorFlow: heap OOB read in type inference engine
CVE-2022-23592 TensorFlow: SavedModel stack overflow via recursive GraphDef
CVE-2022-23591 TensorFlow: DoS via malicious SavedModel GraphDef
CVE-2022-23590 TensorFlow Grappler: DoS via malicious SavedModel
CVE-2022-23589 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