Search papers, labs, and topics across Lattice.
This survey synthesizes recent research on AI/LLM-assisted hardware security verification, categorizing techniques across asset identification, threat modeling, test-plan generation, simulation analysis, formal verification, and countermeasure reasoning. It highlights the potential of AI to automate verification workflows while emphasizing the need for grounding AI outputs in established verification methods. A case study using the NVIDIA Deep Learning Accelerator (NVDLA) demonstrates the practical application of these techniques.
AI can significantly accelerate hardware security verification, but only if its outputs are rigorously validated with simulation, formal methods, and benchmarks.
As hardware systems grow in complexity, security verification must keep up with them. Recently, artificial intelligence (AI) and large language models (LLMs) have started to play an important role in automating several stages of the verification workflow by helping engineers analyze designs, reason about potential threats, and generate verification artifacts. This survey synthesizes recent advances in AI-assisted hardware security verification and organizes the literature along key stages of the workflow: asset identification, threat modeling, security test-plan generation, simulation-driven analysis, formal verification, and countermeasure reasoning. To illustrate how these techniques can be applied in practice, we present a case study using the open-source NVIDIA Deep Learning Accelerator (NVDLA), a representative modern hardware design. Throughout this study, we emphasize that while AI/LLM-based automation can significantly accelerate verification tasks, its outputs must remain grounded in simulation evidence, formal reasoning, and benchmark-driven evaluation to ensure trustworthy hardware security assurance.
