Cross-Trace Verification Protocol: A Framework for Detecting Malicious Code in AI-Generated Programs

Large language models (LLMs) increasingly generate code with minimal human oversight, raising critical concerns about backdoor injection and malicious behavior.

Rather than directly executing potentially malicious code, CTVP leverages the model's own predictions of execution traces across semantically equivalent program transformations.

By analyzing consistency patterns in these predicted traces, we detect behavioral anomalies indicative of backdoors.

Theoretical analysis establishes information-theoretic bounds showing non-gamifiability - adversaries cannot improve through training due to fundamental space complexity constraints.

This work demonstrates that semantic orbit analysis provides a theoretically grounded approach to AI control for code generation tasks, though practical deployment requires addressing the high false positive rates observed in initial evaluations.