Yongwang Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Yongwang Zhao has a total of 81 co-authors. Here are the top co-authors by number of shared publications:
- David Sanan
Singapore Institute of Technology, Singapore, Singapore
8 shared publications Fuyuan Zhang
MPI-SWS
5 shared publications- Kui Ren
Zhejiang University
5 shared publications - Rui Chang
Zhejiang University
5 shared publications - Yang Liu
Department of Obstetrics and Gynecology, The Second Affiliated Hospital of Kunming Medical University, China
4 shared publications - Zhuoruo Zhang
Zhejiang University, Hangzhou, China
4 shared publications
Latest Publications
- Open Access
- 4 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35  (11) , 1-36
Compiler Optimizations-based SMT Simplifications: An In-Depth Study
SMT solvers are a cornerstone in numerous domains, such as program verification, repair, and synthesis. While formula simplification is a crucial preprocessing step that directly impacts solver efficiency, existing approaches predominantly rely on handcrafted heuristics. Recent advances have explored using compiler optimizations to automate and enhance formula simplifications. Despite their promise, the synergy between compiler optimizations and SMT simplifications remains insufficiently understood and underexploited. This article presents a comprehensive study of the interplay between compiler optimizations and SMT formula simplifications. We show that iterative search for optimization configurations significantly improves formula simplifications, yielding a geometric mean speed-up of 2.96 \(\times\) over default solvers and 2.12 \(\times\) over SLOT on large-scale benchmarks. We present strong evidence for the effectiveness of machine learning-based methods in automating the selection of optimization configurations tailored to specific problem instances, achieving geometric mean speed-ups of 1.15 \(\times\) over Z3 and 1.54 \(\times\) over CVC5. Finally, we discuss promising directions for improving the applicability and effectiveness of compiler optimization-driven approaches to SMT simplifications.- 4 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
- Vol. 35  (11) , 1-36
Open AccessCompiler Optimizations-based SMT Simplifications: An In-Depth Study
SMT solvers are a cornerstone in numerous domains, such as program verification, repair, and synthesis. While formula simplification is a crucial preprocessing step that directly impacts solver efficiency, existing approaches predominantly rely on handcrafted heuristics. Recent advances have explored using compiler optimizations to automate and enhance formula simplifications. Despite their promise, the synergy between compiler optimizations and SMT simplifications remains insufficiently understood and underexploited. This article presents a comprehensive study of the interplay between compiler optimizations and SMT formula simplifications. We show that iterative search for optimization configurations significantly improves formula simplifications, yielding a geometric mean speed-up of 2.96 \(\times\) over default solvers and 2.12 \(\times\) over SLOT on large-scale benchmarks. We present strong evidence for the effectiveness of machine learning-based methods in automating the selection of optimization configurations tailored to specific problem instances, achieving geometric mean speed-ups of 1.15 \(\times\) over Z3 and 1.54 \(\times\) over CVC5. Finally, we discuss promising directions for improving the applicability and effectiveness of compiler optimization-driven approaches to SMT simplifications. - Open Access
- 28 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Compiling by Proving in \({\mathbb{K}}\) : From All-Path Reachability Proofs to Single-Step Semantic RulesThe \({\mathbb{K}}\) framework generates language tools from formal semantics and hosts comprehensive semantics for real-world languages including C, Java, JavaScript, and the Ethereum Virtual Machine, with industrial adoption in blockchain verification. However, the generated executors interpret programs by applying semantic rules step by step, causing performance overhead that limits practical scalability. We present compiling by proving , a language-agnostic mechanism that eliminates this overhead. Given a code unit, we use symbolic execution to prove that its specification holds across all execution paths, generating a proof graph that encodes the complete input-output behavior. We compile this proof graph into a single-step rule that directly maps inputs to outputs, replacing step-by-step interpretation with one-step execution. Because the pipeline is language-agnostic, it benefits any language formalized in \({\mathbb{K}}\) . We evaluate on EVM and Rust MIR semantics, showing speedups in concrete and symbolic execution, and demonstrate applications to semantic equivalence verification and compositional smart contract verification.- 28 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Software Engineering and Methodology
Open AccessCompiling by Proving in \({\mathbb{K}}\) : From All-Path Reachability Proofs to Single-Step Semantic RulesThe \({\mathbb{K}}\) framework generates language tools from formal semantics and hosts comprehensive semantics for real-world languages including C, Java, JavaScript, and the Ethereum Virtual Machine, with industrial adoption in blockchain verification. However, the generated executors interpret programs by applying semantic rules step by step, causing performance overhead that limits practical scalability. We present compiling by proving , a language-agnostic mechanism that eliminates this overhead. Given a code unit, we use symbolic execution to prove that its specification holds across all execution paths, generating a proof graph that encodes the complete input-output behavior. We compile this proof graph into a single-step rule that directly maps inputs to outputs, replacing step-by-step interpretation with one-step execution. Because the pipeline is language-agnostic, it benefits any language formalized in \({\mathbb{K}}\) . We evaluate on EVM and Rust MIR semantics, showing speedups in concrete and symbolic execution, and demonstrate applications to semantic equivalence verification and compositional smart contract verification. - 20 January 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20  (6) , 2006201
K-SELinux: formal analysis and verification of SELinux policies via semantic execution
- 20 January 2026
- Published by Springer Nature in Frontiers of Computer Science
- Vol. 20  (6) , 2006201
K-SELinux: formal analysis and verification of SELinux policies via semantic execution
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21  (15566013) , 476-489
PA-Boot: A Formally Verified Authentication Protocol for Multiprocessor Secure Boot Under Hardware Supply-Chain Attacks
Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. In this paper, we investigate critical stages of the multiprocessor system boot process and identify a new, prevalent hardware supply-chain attack surface that can bypass secure boot due to the absence of processor-authentication mechanisms. To defend against such attacks, in this paper, we present PA-Boot, the first formally verified processor-authentication protocol for secure boot in multiprocessor systems. PA-Boot is proved functionally correct and is guaranteed to detect multiple adversarial behaviors, such as processor replacements and man-in-the-middle attacks. The fine-grained formalization of PA-Boot and its fully mechanized security proofs are carried out in the Isabelle/HOL theorem prover with 348 lemmas/theorems and ~7,100 LoC. We further implement in C an instance of PA-Boot. Experiments on the proof-of-concept implementation indicate that PA-Boot can effectively identify boot-process attacks with a minor overhead (4.98% on Linux boot process) and thereby improve the security of multiprocessor systems.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21  (15566013) , 476-489
PA-Boot: A Formally Verified Authentication Protocol for Multiprocessor Secure Boot Under Hardware Supply-Chain Attacks
Hardware supply-chain attacks are raising significant security threats to the boot process of multiprocessor systems. In this paper, we investigate critical stages of the multiprocessor system boot process and identify a new, prevalent hardware supply-chain attack surface that can bypass secure boot due to the absence of processor-authentication mechanisms. To defend against such attacks, in this paper, we present PA-Boot, the first formally verified processor-authentication protocol for secure boot in multiprocessor systems. PA-Boot is proved functionally correct and is guaranteed to detect multiple adversarial behaviors, such as processor replacements and man-in-the-middle attacks. The fine-grained formalization of PA-Boot and its fully mechanized security proofs are carried out in the Isabelle/HOL theorem prover with 348 lemmas/theorems and ~7,100 LoC. We further implement in C an instance of PA-Boot. Experiments on the proof-of-concept implementation indicate that PA-Boot can effectively identify boot-process attacks with a minor overhead (4.98% on Linux boot process) and thereby improve the security of multiprocessor systems.
- Open Access
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2789-2803
Generalized Security-Preserving Refinement for Concurrent Systems
- 19 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 2789-2803
Open AccessGeneralized Security-Preserving Refinement for Concurrent Systems
- Open Access
Compiling by Proving: Language-Agnostic Automatic Optimization from Formal Semantics
Verification proofs encode complete program behavior, yet we discard them after checking correctness. We present compiling by proving, a paradigm that transforms these proofs into optimized execution rules. By constructing All-Path Reachability Proofs through symbolic execution and compiling their graph structure, we consolidate many semantic rewrites into single rules while preserving correctness by construction. We implement this as a language-agnostic extension to the K framework. Evaluation demonstrates performance improvements across different compilation scopes: opcode-level optimizations show consistent speedups, while whole-program compilation achieves orders of magnitude greater performance gains.
Open AccessCompiling by Proving: Language-Agnostic Automatic Optimization from Formal Semantics
Verification proofs encode complete program behavior, yet we discard them after checking correctness. We present compiling by proving, a paradigm that transforms these proofs into optimized execution rules. By constructing All-Path Reachability Proofs through symbolic execution and compiling their graph structure, we consolidate many semantic rewrites into single rules while preserving correctness by construction. We implement this as a language-agnostic extension to the K framework. Evaluation demonstrates performance improvements across different compilation scopes: opcode-level optimizations show consistent speedups, while whole-program compilation achieves orders of magnitude greater performance gains.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 6983-6997
Tacco: A Framework for Ensuring the Security of Real-World TEEs via Formal Verification
Trusted Execution Environment (TEE) provides isolation for sensitive data in electronic devices and its compromise can lead to enormous losses. TEE's information-flow security is essential and can be robustly ensured by formal methods. Nevertheless, the cross-domain API invocation of TEE is intricate for information-flow analysis, and the service provider on the TEE, i.e., trusted application, brings complexity to the TEE specification and verification. Existing research seldom delves into general TEEs that are compliant with GlobalPlatform (GP), which is an important and universal TEE standard. Furthermore, they do not align with the requirements for Common Criteria certification. In this paper, we propose a TEE-applicable and Common Criteria-oriented framework to specify and verify the information-flow security of GP TEE, which is applied to the verification of the real-world commercial MiTEE. Firstly, we present a framework for TEE that aligns with the requirements of Common Criteria's highest assurance level (EAL 7). It incorporates a domainswitch based mechanism to model the cross-domain TEE API invocation and a parameterized modeling approach to handle trusted applications. Secondly, we model GlobalPlatform-compliant TEE with the framework as GP TEE security model layer and function layer, which are reusable for all GP TEEs. Thirdly, we specify MiTEE as the MiTEE design layer that refines GP TEE model. Lastly, we verify the information-flow security of GP TEE and MiTEE via theorem proving and uncover four critical vulnerabilities in MiTEE. This work contributes to MiTEE's acquirement of an EAL 5+ certificate. All works are carried out in Isabelle/HOL, with nearly 32000 lines of code.
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22  (6) , 6983-6997
Tacco: A Framework for Ensuring the Security of Real-World TEEs via Formal Verification
Trusted Execution Environment (TEE) provides isolation for sensitive data in electronic devices and its compromise can lead to enormous losses. TEE's information-flow security is essential and can be robustly ensured by formal methods. Nevertheless, the cross-domain API invocation of TEE is intricate for information-flow analysis, and the service provider on the TEE, i.e., trusted application, brings complexity to the TEE specification and verification. Existing research seldom delves into general TEEs that are compliant with GlobalPlatform (GP), which is an important and universal TEE standard. Furthermore, they do not align with the requirements for Common Criteria certification. In this paper, we propose a TEE-applicable and Common Criteria-oriented framework to specify and verify the information-flow security of GP TEE, which is applied to the verification of the real-world commercial MiTEE. Firstly, we present a framework for TEE that aligns with the requirements of Common Criteria's highest assurance level (EAL 7). It incorporates a domainswitch based mechanism to model the cross-domain TEE API invocation and a parameterized modeling approach to handle trusted applications. Secondly, we model GlobalPlatform-compliant TEE with the framework as GP TEE security model layer and function layer, which are reusable for all GP TEEs. Thirdly, we specify MiTEE as the MiTEE design layer that refines GP TEE model. Lastly, we verify the information-flow security of GP TEE and MiTEE via theorem proving and uncover four critical vulnerabilities in MiTEE. This work contributes to MiTEE's acquirement of an EAL 5+ certificate. All works are carried out in Isabelle/HOL, with nearly 32000 lines of code.
- Open Access
HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
Formal methods is pivotal for verifying the reliability of critical systems through rigorous mathematical proofs. However, its adoption is hindered by labor-intensive manual proofs and the expertise required to use theorem provers. Recent advancements in large language models (LLMs) offer new opportunities for automated theorem proving. Two promising approaches are generating tactics step by step and generating a whole proof directly with an LLM. However, existing work makes no attempt to combine the two approaches. In this work, we introduce HybridProver, a dual-model proof synthesis framework that combines tactic-based generation and whole-proof synthesis to harness the benefits of both approaches. HybridProver generates whole proof candidates for evaluation directly, then extracts proof sketches from those candidates. It then uses a tactic-based generation model that integrates automated tools to complete the sketches via stepwise refinement. We implement HybridProver for the Isabelle theorem prover and fine-tune LLMs on our optimized Isabelle datasets. Evaluation on the miniF2F dataset illustrates HybridProver's effectiveness. We achieve a 59.4% success rate on miniF2F, where the previous SOTA is 56.1%. Our ablation studies show that this SOTA result is attributable to combining whole-proof and tactic-based generation. Additionally, we show how the dataset quality, training parameters, and sampling diversity affect the final result during automated theorem proving with LLMs. All of our code, datasets, and LLMs are open source.
Open AccessHybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement
Formal methods is pivotal for verifying the reliability of critical systems through rigorous mathematical proofs. However, its adoption is hindered by labor-intensive manual proofs and the expertise required to use theorem provers. Recent advancements in large language models (LLMs) offer new opportunities for automated theorem proving. Two promising approaches are generating tactics step by step and generating a whole proof directly with an LLM. However, existing work makes no attempt to combine the two approaches. In this work, we introduce HybridProver, a dual-model proof synthesis framework that combines tactic-based generation and whole-proof synthesis to harness the benefits of both approaches. HybridProver generates whole proof candidates for evaluation directly, then extracts proof sketches from those candidates. It then uses a tactic-based generation model that integrates automated tools to complete the sketches via stepwise refinement. We implement HybridProver for the Isabelle theorem prover and fine-tune LLMs on our optimized Isabelle datasets. Evaluation on the miniF2F dataset illustrates HybridProver's effectiveness. We achieve a 59.4% success rate on miniF2F, where the previous SOTA is 56.1%. Our ablation studies show that this SOTA result is attributable to combining whole-proof and tactic-based generation. Additionally, we show how the dataset quality, training parameters, and sampling diversity affect the final result during automated theorem proving with LLMs. All of our code, datasets, and LLMs are open source.
- Open Access
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9  (OOPSLA1) , 1-27
A Complete Formal Semantics of eBPF Instruction Set Architecture for Solana
We present the first formal semantics for the Solana eBPF bytecode language used in smart contracts on the Solana blockchain platform. Our formalization accurately captures all binary-level instructions of the Solana eBPF instruction set architecture. This semantics is structured in a small-step style, facilitating the formalization of the Solana eBPF interpreter within Isabelle/HOL. We provide a semantics validation framework that extracts an executable semantics from our formalization to test against the original implementation of the Solana eBPF interpreter. This approach introduces a novel lightweight and non-invasive method to relax the limitations of the existing Isabelle/HOL extraction mechanism. Furthermore, we illustrate potential applications of our semantics in the formalization of the main components of the Solana eBPF virtual machine.
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9  (OOPSLA1) , 1-27
Open AccessA Complete Formal Semantics of eBPF Instruction Set Architecture for Solana
We present the first formal semantics for the Solana eBPF bytecode language used in smart contracts on the Solana blockchain platform. Our formalization accurately captures all binary-level instructions of the Solana eBPF instruction set architecture. This semantics is structured in a small-step style, facilitating the formalization of the Solana eBPF interpreter within Isabelle/HOL. We provide a semantics validation framework that extracts an executable semantics from our formalization to test against the original implementation of the Solana eBPF interpreter. This approach introduces a novel lightweight and non-invasive method to relax the limitations of the existing Isabelle/HOL extraction mechanism. Furthermore, we illustrate potential applications of our semantics in the formalization of the main components of the Solana eBPF virtual machine.
- Open Access
Psychometric-Based Evaluation for Theorem Proving with Large Language Models
Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, this evaluation method overlooks the varying importance of theorems. As a result, it fails to highlight the real performance disparities between LLMs and leads to high evaluation costs. This study proposes a psychometric-based evaluation method for theorem proving with LLMs, comprising two main components: Dataset Annotation and Adaptive Evaluation. First, we propose a metric calculation method to annotate the dataset with difficulty and discrimination metrics. Specifically, we annotate each theorem in the miniF2F dataset and grade them into varying difficulty levels according to the performance of LLMs, resulting in an enhanced dataset: miniF2F-Graded. Experimental results show that the difficulty grading in miniF2F-Graded better reflects the theorem difficulty perceived by LLMs. Secondly, we design an adaptive evaluation method to dynamically select the most suitable theorems for testing based on the annotated metrics and the real-time performance of LLMs. We apply this method to evaluate 10 LLMs. The results show that our method finely highlights the performance disparities between LLMs. It also reduces evaluation costs by using only 23% of the theorems in the dataset.
Open AccessPsychometric-Based Evaluation for Theorem Proving with Large Language Models
Large language models (LLMs) for formal theorem proving have become a prominent research focus. At present, the proving ability of these LLMs is mainly evaluated through proof pass rates on datasets such as miniF2F. However, this evaluation method overlooks the varying importance of theorems. As a result, it fails to highlight the real performance disparities between LLMs and leads to high evaluation costs. This study proposes a psychometric-based evaluation method for theorem proving with LLMs, comprising two main components: Dataset Annotation and Adaptive Evaluation. First, we propose a metric calculation method to annotate the dataset with difficulty and discrimination metrics. Specifically, we annotate each theorem in the miniF2F dataset and grade them into varying difficulty levels according to the performance of LLMs, resulting in an enhanced dataset: miniF2F-Graded. Experimental results show that the difficulty grading in miniF2F-Graded better reflects the theorem difficulty perceived by LLMs. Secondly, we design an adaptive evaluation method to dynamically select the most suitable theorems for testing based on the annotated metrics and the real-time performance of LLMs. We apply this method to evaluate 10 LLMs. The results show that our method finely highlights the performance disparities between LLMs. It also reduces evaluation costs by using only 23% of the theorems in the dataset.