hylock: hybrid logic locking based on structural fuzzing for resisting learning-based attacks

The growing popularity of the fabless manufacturing model has increased the importance of logic locking as a key-based method for intellectual property (ip) protection. recently, machine learning-based attacks have broken most existing locks by finding structural traces or undoing optimizations that obfuscate them. in this paper, we introduce structural fuzzing as a simple, random non-optimizing heuristic that can obfuscate the lock against learning-based attacks, preventing the attacker from predicting the key. we proceed to apply structural fuzzing to multiplexer-based logic locking and propose hylock, a lock with improved resilience against learning-based attacks. in the benchmarks, when compared with a state of the art lock, there is on average a 17% decrease in the number of correctly predicted key bits.