LLM for SoC Security: A Paradigm Shift

Abstract

As the ubiquity and complexity of system-on-chip (SoC) designs increase across electronic devices, the task of incorporating security into an SoC design flow poses significant challenges. Existing security solutions are inadequate to provide effective verification of modern SoC designs due to their limitations in scalability, comprehensiveness, and adaptability. On the other hand, Large Language Models (LLMs) are celebrated for their remarkable success in natural language understanding, advanced reasoning, and program synthesis tasks. Recognizing an opportunity, our research delves into leveraging the emergent capabilities of Generative Pre-trained Transformers (GPTs) to address the existing gaps in SoC security, aiming for a more efficient, scalable, and adaptable methodology. By integrating LLMs into the SoC security verification paradigm, we open a new frontier of possibilities and challenges to ensure the security of increasingly complex SoCs. This paper offers an in-depth analysis of existing works, showcases practical case studies, demonstrates comprehensive experiments, and provides useful promoting guidelines. We also present the achievements, prospects, and challenges of employing LLM in different SoC security verification tasks.

42 pages

References in corpus (45)

• PaLM: Scaling Language Modeling with Pathways
• Evaluating Large Language Models Trained on Code
• Emergent Abilities of Large Language Models
• Self-Consistency Improves Chain of Thought Reasoning in Language Models
• ReAct: Synergizing Reasoning and Acting in Language Models
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models
• Capabilities of GPT-4 on Medical Challenge Problems
• Code Llama: Open Foundation Models for Code
• PaLM-E: An Embodied Multimodal Language Model
• Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
• Least-to-Most Prompting Enables Complex Reasoning in Large Language Models
• BloombergGPT: A Large Language Model for Finance
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
• CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
• Self-Refine: Iterative Refinement with Self-Feedback
• Chip-Chat: Challenges and Opportunities in Conversational Hardware Design
• StarCoder: may the source be with you!
• InCoder: A Generative Model for Code Infilling and Synthesis
• Getting pwn'd by AI: Penetration Testing with Large Language Models
• AugGPT: Leveraging ChatGPT for Text Data Augmentation
• How Effective Are Neural Networks for Fixing Security Vulnerabilities
• RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution
• WizardCoder: Empowering Code Large Language Models with Evol-Instruct
• Teaching Large Language Models to Self-Debug
• Complexity-Based Prompting for Multi-Step Reasoning
• Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT
• Language Models can Solve Computer Tasks
• Pretrained Language Models for Text Generation: A Survey
• CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
• SantaCoder: don't reach for the stars!
• LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging
• Faithful Reasoning Using Large Language Models
• Fuzzing Hardware Like Software
• ChipNeMo: Domain-Adapted LLMs for Chip Design
• ChipGPT: How far are we from natural language hardware design
• PanGu-Coder: Program Synthesis with Function-Level Language Modeling
• Training and Evaluating a Jupyter Notebook Data Science Assistant
• AutoChip: Automating HDL Generation Using LLM Feedback
• Unlocking Hardware Security Assurance: The Potential of LLMs
• Isolating Compiler Bugs by Generating Effective Witness Programs with Large Language Models
• Using LLMs to Facilitate Formal Verification of RTL
• DIVAS: An LLM-based End-to-End Framework for SoC Security Analysis and Policy-based Protection
• PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback
• RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models
• Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions

Cited by in corpus (1)

• GenDFIR: Advancing Cyber Incident Timeline Analysis Through Retrieval Augmented Generation and Large Language Models