AI Component
Inference
Inference-layer vulnerabilities target the serving infrastructure that runs ML models in production — including vLLM, TensorRT, Triton, and custom serving endpoints.
536
Total CVEs
27
Pages
Page 14 of 27
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| HIGH | CVE-2022-35988 | TensorFlow: GPU DoS via empty input to matrix_rank op | tensorflow | 7.5 |
| HIGH | CVE-2022-35989 | TensorFlow: MaxPool GPU kernel DoS via oversized ksize | tensorflow | 7.5 |
| HIGH | CVE-2022-35990 | TensorFlow: DoS via quantization gradient rank check | tensorflow | 7.5 |
| HIGH | CVE-2022-36018 | TensorFlow: RaggedTensor CHECK fail remote DoS | tensorflow | 7.5 |
| HIGH | CVE-2022-36019 | TensorFlow: DoS via FakeQuant tensor rank mismatch | tensorflow | 7.5 |
| HIGH | CVE-2022-36026 | TensorFlow: DoS via QuantizeAndDequantizeV3 CHECK fail | tensorflow | 7.5 |
| HIGH | CVE-2022-35991 | TensorFlow: DoS via TensorListScatter CHECK fail | tensorflow | 7.5 |
| HIGH | CVE-2022-35992 | TensorFlow: DoS via malformed TensorList element shape | tensorflow | 7.5 |
| HIGH | CVE-2022-35993 | TensorFlow: DoS via malformed SetSize tensor shape | tensorflow | 7.5 |
| HIGH | CVE-2022-35994 | TensorFlow: CollectiveGather assertion DoS via scalar | tensorflow | 7.5 |
| HIGH | CVE-2022-35995 | TensorFlow: DoS via AudioSummaryV2 CHECK failure | tensorflow | 7.5 |
| HIGH | CVE-2022-35996 | TensorFlow: Conv2D DoS via empty input tensor | tensorflow | 7.5 |
| HIGH | CVE-2022-35997 | TensorFlow: CHECK-fail DoS in tf.sparse.cross op | tensorflow | 7.5 |
| HIGH | CVE-2022-35998 | TensorFlow: DoS via EmptyTensorList CHECK fail | tensorflow | 7.5 |
| HIGH | CVE-2022-35999 | TensorFlow: DoS via empty Conv2DBackpropInput tensors | tensorflow | 7.5 |
| HIGH | CVE-2022-36000 | TensorFlow: null deref crashes MLIR graph conversion | tensorflow | 7.5 |
| HIGH | CVE-2022-36001 | TensorFlow: DoS via type confusion in DrawBoundingBoxes | tensorflow | 7.5 |
| HIGH | CVE-2022-36002 | TensorFlow: DoS via Unbatch assertion failure | tensorflow | 7.5 |
| HIGH | CVE-2022-36003 | TensorFlow: DoS via RandomPoissonV2 large input | tensorflow | 7.5 |
| HIGH | CVE-2022-36004 | TensorFlow: DoS via tf.random.gamma CHECK assertion | tensorflow | 7.5 |
AI Threat Alert