AI Threat Alert
Attack Type
Data Extraction
Data extraction attacks target AI/ML systems to exfiltrate training data, model weights, user conversations, or other sensitive information. These vulnerabilities are critical in multi-tenant AI deployments.
395
Total CVEs
20
Pages
Page 3 of 20
Current
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| MEDIUM | CVE-2021-37687 | TFLite: heap OOB read via negative indices in GatherNd | tensorflow | 5.5 |
| HIGH | CVE-2021-41210 | TensorFlow: heap OOB read in SparseCountSparseOutput | tensorflow | 7.1 |
| HIGH | CVE-2021-41211 | TensorFlow: heap OOB read in QuantizeV2 shape inference | tensorflow | 7.1 |
| HIGH | CVE-2021-41212 | TensorFlow: heap OOB read in ragged.cross shape inference | tensorflow | 7.1 |
| HIGH | CVE-2021-41226 | TensorFlow: heap OOB in SparseBinCount, crash/disclosure | tensorflow | 7.1 |
| MEDIUM | CVE-2021-41227 | TensorFlow: OOB read in ImmutableConst leaks memory | tensorflow | 5.5 |
| HIGH | CVE-2022-21726 | TensorFlow: heap OOB read in Dequantize op allows RCE | tensorflow | 8.8 |
| HIGH | CVE-2022-21730 | TensorFlow: OOB read leaks heap memory, enables DoS | tensorflow | 8.1 |
| HIGH | CVE-2022-23560 | TFLite: OOB read/write in sparse tensor → RCE | tensorflow | 8.8 |
| HIGH | CVE-2022-23592 | TensorFlow: heap OOB read in type inference engine | tensorflow | 8.1 |
| CRITICAL | CVE-2022-35937 | TensorFlow: GatherNd OOB read crashes inference servers | tensorflow | 9.1 |
| CRITICAL | CVE-2022-35938 | TensorFlow: OOB read in GatherNd causes crash/data leak | tensorflow | 9.1 |
| CRITICAL | CVE-2022-41880 | TensorFlow: heap OOB read in candidate sampler op | tensorflow | 9.1 |
| CRITICAL | CVE-2022-41902 | TensorFlow Grappler: OOB read/crash via crafted model | tensorflow | 9.1 |
| CRITICAL | CVE-2022-41910 | TensorFlow Grappler: OOB read crashes or leaks memory | tensorflow | 9.1 |
| CRITICAL | CVE-2023-43654 | TorchServe: SSRF + RCE via unrestricted model URL loading | torchserve | 9.8 |
| MEDIUM | CVE-2024-31584 | PyTorch: OOB read in mobile model loader leaks memory | pytorch | 5.5 |
| HIGH | CVE-2024-35199 | TorchServe: default gRPC exposure allows unauth inference | torchserve | 8.2 |
| MEDIUM | CVE-2024-6577 | TorchServe: unverified S3 bucket exposes benchmark data | 6.3 | |
| MEDIUM | CVE-2025-2999 | PyTorch: memory corruption in RNN sequence unpacking | pytorch | 5.3 |