Data and model poisoning
Description
Pre-training, fine-tuning, or embedding data is manipulated to alter the model's behavior, compromise integrity, or degrade performance.
Impact
- Alteration of the model's behavior.
- Compromise of integrity.
- Degradation of performance.
- Increased error rates.
- Embedding of malicious instructions.
Recommendation
- SSO and MFA to limit who can access your data and AI platform.
- Enforce data quality checks on batch and streaming data before they make it to the datasets.
- Validate and audit all training datasets.
- Implement sandboxing.
Threat
Authenticated attacker from the Internet.
Expected Remediation Time
⌚ 60 minutes.
Score
Default score using CVSS 3.1. It may change depending on the context of the src.
Base
- Attack vector: N
- Attack complexity: H
- Privileges required: L
- User interaction: N
- Scope: U
- Confidentiality: L
- Integrity: L
- Availability: L
Temporal
- Exploit code maturity: P
- Remediation level: O
- Report confidence: C
Result
- Vector string: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:L/A:L/E:P/RL:O/RC:C
- Score:
- Base: 5.0
- Temporal: 4.5
- Severity:
- Base: Medium
- Temporal: Medium
Score 4.0
Default score using CVSS 4.0. It may change depending on the context of the src.
Base 4.0
- Attack vector: N
- Attack complexity: H
- Attack Requirements: N
- Privileges required: L
- User interaction: N
- Confidentiality (VC): L
- Integrity (VI): L
- Availability (VA): L
- Confidentiality (SC): N
- Integrity (SI): N
- Availability (SA): N
Threat 4.0
- Exploit maturity: P
Result 4.0
- Vector string: CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P
- Score:
- CVSS-BT: 1.3
- Severity:
- CVSS-BT: Low
Compliant code
Non compliant code
Requirements
- 173.Discard unsafe inputs
- 262.Verify third-party components
- 383.Sandboxing to limit model exposure to unverified data sources
Fixes
