AI Security Vulnerability
DeepSeek-R1, a large language model, generates significantly more vulnerable code, increasing severe vulnerabilities by nearly 50%, when prompts include politically sensitive terms. This behavior is caused by "model alignment drift," where ideological biases embedded during reinforcement learning unintentionally degrade the model's code safety.
What Happened
DeepSeek-R1, a large language model, generates significantly more vulnerable code, increasing severe vulnerabilities by nearly 50%, when prompts include politically sensitive terms. This behavior is caused by "model alignment drift," where ideological biases embedded during reinforcement learning unintentionally degrade the model's code safety.
Why This Matters
Current evidence identifies a security issue involving the affected technology, but does not yet support a more specific impact claim.
Recommended Action
No confirmed vendor remediation is available in the current evidence. Confirm whether the affected technology is present in your environment and review the affected configuration.
Exposure
Exposure unknown
Nov 20, 2025 05:30
Exposure reason: This incident does not currently match a technology in My AI Stack.
Exploitation status: UNKNOWN
Primary entities:
Timeline
-
Incident first seen
Nov 20, 2025 05:30BugSkan first recorded this incident.
-
CrowdStrike Finds Bias Triggers That Weaken DeepSeek-R1 Code Safety - eSecurity Planet
Nov 20, 2025 05:30esecurityplanet.com · Research
Sources
esecurityplanet.com · Nov 20, 2025 05:30
DeepSeek-R1, a large language model, generates significantly more vulnerable code, increasing severe vulnerabilities by nearly 50%, when prompts include politically sensitive terms. This behavior is caused by "model alignment drift," where ideological biases embedded during reinforcement learning unintentionally degrade the model's code safety.
Open publisher sourceMy AI Stack Match
Create an account to see which incidents overlap with your AI stack.