AI Threat Alert
Training Data
Training data is both the model's most valuable input and its most underprotected one. Three problem classes dominate. First, poisoning: an attacker who can influence a public dataset, a web crawl, or a fine-tuning corpus can plant backdoors or biases that survive into the deployed model — BadNets-style attacks on image classifiers, trigger-phrase attacks on LLMs, and reward-hacking on RLHF datasets. Second, memorization and leakage: models can regurgitate verbatim training data, exposing PII and copyrighted content; this has driven the active New York Times v. OpenAI litigation and is a recurring GDPR concern. Third, provenance: when training data origins are unclear, downstream users inherit legal and security risk they can't assess. EU AI Act Article 10 (Data Governance) and ISO 42001 Annex A treat training-data quality as a controlled asset. Defenses: data lineage tracking, deduplication, PII scrubbing before training, and adversarial training against known trigger families.
| Severity | CVE | Headline | Package | CVSS |
|---|---|---|---|---|
| CRITICAL | CVE-2024-27132 | MLflow: XSS in recipes enables client-side RCE | mlflow | 9.6 |
| HIGH | CVE-2024-1483 | MLflow: path traversal exposes arbitrary server files | mlflow | 7.5 |
| HIGH | CVE-2024-1560 | MLflow: path traversal allows arbitrary directory deletion | mlflow | 8.1 |
| HIGH | CVE-2024-1593 | MLflow: path traversal via ';' smuggling exposes files | mlflow | 7.5 |
| HIGH | CVE-2024-1594 | MLflow: path traversal via URI fragment reads arbitrary files | mlflow | 7.5 |
| MEDIUM | CVE-2024-4263 | MLflow: broken access control allows artifact deletion | mlflow | 5.4 |
| HIGH | CVE-2024-37060 | MLflow: RCE via deserialization in crafted Recipes | mlflow | 8.8 |
| HIGH | CVE-2024-37061 | MLflow: RCE via malicious MLproject file execution | mlflow | 8.8 |
| HIGH | CVE-2024-0520 | MLflow: path traversal enables RCE via dataset loading | mlflow | 8.8 |
| HIGH | CVE-2024-2928 | MLflow: URI fragment LFI exposes arbitrary files | mlflow | 7.5 |
| HIGH | CVE-2024-27134 | MLflow: local privilege escalation via spark_udf ToCToU | mlflow | 7.0 |
| HIGH | CVE-2024-8859 | MLflow: path traversal allows arbitrary file read via DBFS | mlflow | 7.5 |
| HIGH | CVE-2025-1473 | MLflow: CSRF in signup allows rogue account creation | mlflow | 7.1 |
| MEDIUM | CVE-2025-1474 | MLflow: passwordless accounts enable persistent backdoor | mlflow | 5.5 |
| CRITICAL | CVE-2025-11200 | mlflow: security flaw enables exploitation | mlflow | 9.8 |
| HIGH | CVE-2025-10279 | mlflow: security flaw enables exploitation | mlflow | 7.0 |
| MEDIUM | CVE-2023-2800 | Transformers: temp file race condition allows local DoS | transformers | 4.7 |
| HIGH | CVE-2025-33213 | NVIDIA: Deserialization enables RCE | 8.8 | |
| HIGH | CVE-2025-33233 | NVIDIA: Code Injection enables RCE | 7.8 | |
| CRITICAL | CVE-2024-52803 | LlamaFactory: RCE via OS command injection in training | llamafactory | 9.8 |