AI Threat Alert
AI Component
Inference
Inference-layer vulnerabilities target the serving infrastructure that runs ML models in production — including vLLM, TensorRT, Triton, and custom serving endpoints.
535
Total CVEs
27
Pages
Page 13 of 27
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| HIGH | CVE-2022-35960 | TensorFlow: DoS via malformed TensorListReserve input | tensorflow | 7.5 |
| HIGH | CVE-2022-35963 | TensorFlow: DoS via FractionalAvgPoolGrad overflow | tensorflow | 7.5 |
| HIGH | CVE-2022-35964 | TensorFlow: remote DoS via BlockLSTMGradV2 validation | tensorflow | 7.5 |
| HIGH | CVE-2022-35965 | TensorFlow: NULL deref DoS via empty tensor input | tensorflow | 7.5 |
| HIGH | CVE-2022-35966 | TensorFlow: DoS via QuantizedAvgPool input validation | tensorflow | 7.5 |
| HIGH | CVE-2022-35967 | TensorFlow: DoS via QuantizedAdd tensor rank flaw | tensorflow | 7.5 |
| HIGH | CVE-2022-35968 | TensorFlow: DoS via AvgPoolGrad shape validation failure | tensorflow | 7.5 |
| HIGH | CVE-2022-35970 | TensorFlow: DoS via malformed QuantizedInstanceNorm tensors | tensorflow | 7.5 |
| HIGH | CVE-2022-35971 | TensorFlow: DoS via invalid quantization tensor rank | tensorflow | 7.5 |
| HIGH | CVE-2022-35972 | TensorFlow: DoS via QuantizedBiasAdd rank validation | tensorflow | 7.5 |
| HIGH | CVE-2022-35973 | TensorFlow: DoS via QuantizedMatMul input validation | tensorflow | 7.5 |
| HIGH | CVE-2022-35974 | TensorFlow: DoS via nonscalar quantization op input | tensorflow | 7.5 |
| HIGH | CVE-2022-35979 | TensorFlow: DoS via nonscalar input in QuantizedRelu | tensorflow | 7.5 |
| HIGH | CVE-2022-35981 | TensorFlow: DoS via FractionalMaxPoolGrad assertion | tensorflow | 7.5 |
| HIGH | CVE-2022-35982 | TensorFlow: DoS via invalid SparseBincount input | tensorflow | 7.5 |
| HIGH | CVE-2022-35983 | TensorFlow: DoS via Save/SaveSlices dtype CHECK fail | tensorflow | 7.5 |
| HIGH | CVE-2022-35984 | TensorFlow: int64 type mismatch triggers remote DoS | tensorflow | 7.5 |
| HIGH | CVE-2022-35985 | TensorFlow: DoS via malformed LRNGrad tensor input | tensorflow | 7.5 |
| HIGH | CVE-2022-35986 | TensorFlow: RaggedBincount DoS crashes inference server | tensorflow | 7.5 |
| HIGH | CVE-2022-35987 | TensorFlow: DoS via DenseBincount shape mismatch | tensorflow | 7.5 |