Last seen November 20, 2025

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.

Technical Severity
Low severity
Lifecycle Status

STABLE

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

My AI Stack Exposure

Exposure unknown

Recommended Response
Last Seen

Nov 20, 2025 05:30

Exposure reason: This incident does not currently match a technology in My AI Stack.

Exploitation status: UNKNOWN

Primary entities:

Remote Code Execution

Timeline

  • Incident first seen
    Nov 20, 2025 05:30

    BugSkan first recorded this incident.

  • CrowdStrike Finds Bias Triggers That Weaken DeepSeek-R1 Code Safety - eSecurity Planet
    Nov 20, 2025 05:30

    esecurityplanet.com · Research

Sources

CrowdStrike Finds Bias Triggers That Weaken DeepSeek-R1 Code Safety - eSecurity Planet

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 source

My AI Stack Match

Want personalized relevance?

Create an account to see which incidents overlap with your AI stack.

← Back to incident intelligence