Code Transformations Detect LLM-Written Python Across Models
ACW applies idempotent semantic-preserving Python rewrites after generation, reaching over 97% accuracy with under 0.1 seconds per function.
Jul 13, 20265 min2402.07518 Code available
All areas of cryptography and security including authentication and public key cryptosystems.
ACW applies idempotent semantic-preserving Python rewrites after generation, reaching over 97% accuracy with under 0.1 seconds per function.
Instruction-level binary features train a classifier that recovers 91.75% of unsafe regions at a 6.16% false positive rate.
A novel abstract domain enables certified robustness guarantees for realistic deep learning models.