CWE-1039: Automated Recognition Mechanism with Inadequate Detection or Handling of Adversarial Input Perturbations
When techniques such as machine learning are used to automatically classify input streams, and those classifications are used for security-critical decisions, then any mistake in classification can introduce a vulnerability that allows attackers to cause the product to make the wrong security decision. If the automated mechanism is not developed or "trained" with enough input data, then attackers may be able to craft malicious input that intentionally triggers the incorrect classification.
Targeted technologies include, but are not necessarily limited to:
- automated speech recognition
- automated image recognition
For example, an attacker might modify road signs or road surface markings to trick autonomous vehicles into misreading the sign/marking and performing a dangerous action.
Modes of Introduction
Phase | Note |
---|---|
Architecture and Design | This issue can be introduced into the automated algorithm itself. |
Applicable Platforms
Type | Class | Name | Prevalence |
---|---|---|---|
Language | Not Language-Specific | ||
Technology | AI/ML |
CVEs Published
CVSS Severity
CVSS Severity - By Year
CVSS Base Score
# CVE | Description | CVSS | EPSS | EPSS Trend (30 days) | Affected Products | Weaknesses | Security Advisories | Exploits | PoC | Pubblication Date | Modification Date |
---|---|---|---|---|---|---|---|---|---|---|---|
# CVE | Description | CVSS | EPSS | EPSS Trend (30 days) | Affected Products | Weaknesses | Security Advisories | PoC | Pubblication Date | Modification Date |