Search papers, labs, and topics across Lattice.
This paper introduces an agentic LLM-driven framework for automating hardware netlist obfuscation, tackling the challenge of protecting integrated circuit IP in untrusted supply chains. The framework decomposes the obfuscation process into specialized stages including retrieval-grounded planning, lock-plan generation, netlist compilation, functional verification, and security evaluation. Experiments on ISCAS-85 benchmarks demonstrate the generation of functionally correct locked netlists, but also reveal that SAT attacks remain effective, highlighting limitations of the current approach.
LLMs can now automatically generate obfuscated hardware netlists, but don't expect Fort Knox: SAT attacks still crack them.
The globalization of integrated circuit (IC) design and manufacturing has increased the exposure of hardware intellectual property (IP) to untrusted stages of the supply chain, raising concerns about reverse engineering, piracy, tampering, and overbuilding. Hardware netlist obfuscation is a promising countermeasure, but automating the generation of functionally correct and security-relevant obfuscated circuits remains challenging, particularly for benchmark-scale designs. This paper presents an agentic, large language model (LLM)-driven framework for automated hardware netlist obfuscation. The proposed framework combines retrieval-grounded planning, structured lock-plan generation, deterministic netlist compilation, functional verification, and SAT-based security evaluation. Rather than a single prompt-to-output generation step, the framework decomposes the task into specialized stages for circuit analysis, synthesis, verification, and attack evaluation. We evaluate the framework on ISCAS-85 benchmarks using functional equivalence checking and SAT-based attacks. Results show that the framework generates correct locked netlists while introducing measurable output corruption under incorrect keys, while SAT attacks remain effective. These findings highlight both the potential and current limitations of agentic LLM-driven obfuscation.
