Publications
An asterisk marks corresponding authorship. Filter by research theme below.
Books and book chapters
-
Formal Methods and Software Engineering — 26th International Conference on Formal Engineering Methods, ICFEM 2025
Lecture Notes in Computer Science 16229, Springer 2026, ISBN 978-981-95-4212-3
-
Research Progress and Trends on Formal Verification of Artificial Intelligence Systems
CCF 2019–2020 Progress Report on Chinese Computer Science and Technology, China Machine Press, pages 491–539, 2020
2026
-
Hybrid Refinement Logic
Journal of Software (accepted)
-
Sound and Efficient Statistical Model Checking for Probabilities and Bounded Rewards
41st IEEE/ACM International Conference on Automated Software Engineering, Munich, Oct 2026
-
Rounding-Guided Backdoor Injection in Deep Learning Model Quantization
Network and Distributed System Security Symposium, San Diego, Feb 2026 · arXiv
-
LLMQuA: Practical Backdoor Injection on Large Language Model Quantization
The Web Conference, Dubai, Apr 2026
-
Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents
IEEE Transactions on Software Engineering (accepted) · arXiv · code
-
S-Eval: Towards Automated Safety Evaluation with Enhancement for Large Language Models
ACM Transactions on Software Engineering and Methodology (accepted)
-
Prompting Frameworks for Large Language Models: A Survey
ACM Computing Surveys · paper · code · AGI Summit best paper award
-
Synthesis of Sensor Deception Attacks against Security for Timed Supervisory Control Systems
37th IEEE International Symposium on Software Reliability Engineering, Cyprus, Oct 2026
-
A Review on Software Formal Verification Empowered by Large Language Models
Journal of Software (accepted)
-
A2R: A Hybrid Activation-Attention Framework for Enhancing Large Language Model Reliability
Expert Systems with Applications (accepted)
-
PRUNE: A Patching Based Repair Framework for Certifiable and Privacy-Robust Unlearning of Neural Networks
Neural Networks (accepted)
2025
-
Generalized Security-Preserving Refinement for Concurrent Systems
32nd ACM Conference on Computer and Communications Security, Taipei, Oct 2025 · paper
-
Provable Repair of Deep Neural Network Defects through Pre-image Synthesis and Property Refinement
32nd ACM Conference on Computer and Communications Security, Taipei, Oct 2025 · paper
-
LLM-aided Automatic Modelling for Security Protocol Verification
47th International Conference on Software Engineering, Ottawa, Apr 2025 (21.3% acceptance) · paper
-
Provable Fairness Repair for Deep Neural Networks
40th IEEE/ACM International Conference on Automated Software Engineering, Seoul, Nov 2025 · paper
-
Securing Millions of Decentralized Identities in Alipay Super App with End-to-End Formal Verification
Industry showcase track, 40th IEEE/ACM International Conference on Automated Software Engineering, Seoul, Nov 2025
-
Quantitative Runtime Monitoring of Ethereum Transaction Attacks
The Web Conference, Sydney, Apr 2025 (19.8% acceptance) · paper
-
S-Eval: Automatic and Adaptive Test Generation for Benchmarking Safety Evaluation of Large Language Models
34th International Symposium on Software Testing and Analysis, Trondheim, Jun 2025 (19.4% acceptance) · paper · code · leaderboard
-
Patch Synthesis for Property Repair of Deep Neural Networks
47th International Conference on Software Engineering, Ottawa, Apr 2025 (21.3% acceptance)
-
Efficient Function Orchestration for Large Language Models
IEEE Transactions on Software Engineering (accepted) · paper
-
A2E: Black-box Anti-adversarial Example based Watermarking to Verify Federated Unlearning
IEEE Transactions on Dependable and Secure Computing (accepted)
-
OPTSE: Towards Optimal Symbolic Execution
IEEE Transactions on Software Engineering (accepted)
-
Integrating Path Selection for Symbolic Execution and Variable Selection for Constraint Solving
ACM Transactions on Software Engineering and Methodology (accepted)
-
Semantic-aware Testing for Object Detection Systems
Information and Software Technology, 2025
-
Protecting Deep Learning Model Copyrights with Adversarial Example-Free Reuse Detection
IEEE Transactions on Neural Networks and Learning Systems (accepted)
-
PRUNE: A Patching Based Repair Framework for Certifiable Unlearning of Neural Networks
China Automation Conference, Harbin, Sep 2025
-
Fault Localization and Repair for Neural Network based Object Detection
China Automation Conference, Harbin, Sep 2025
-
面向基于国密算法的工业安全协议形式化验证
中国自动化大会, 哈尔滨, 2025
2024
-
VERIFI: Towards Verifiable Federated Unlearning
IEEE Transactions on Dependable and Secure Computing · best paper award runner-up 2024 · paper
-
Scuzer: A Scheduling Optimization Fuzzer for TVM
ACM Transactions on Software Engineering and Methodology (accepted)
-
VeRe: Verification Guided Synthesis for Repairing Deep Neural Networks
46th International Conference on Software Engineering, Lisbon, Apr 2024 (22% acceptance) · paper
-
TeDA: A Testing Framework for Data Usage Auditing in Deep Learning Model Development
33rd International Symposium on Software Testing and Analysis, Vienna, Sep 2024 (20.6% acceptance) · paper
-
Isolation-based Debugging for Neural Networks
33rd International Symposium on Software Testing and Analysis, Vienna, Sep 2024 (20.6% acceptance)
-
Interpretability based Neural Network Repair
33rd International Symposium on Software Testing and Analysis, Vienna, Sep 2024 (20.6% acceptance)
-
FAST: Boosting Uncertainty-based Test Prioritization Methods for Neural Networks via Feature Selection
39th IEEE/ACM International Conference on Automated Software Engineering, Sacramento, Oct 2024
-
Better Pay Attention Whilst Fuzzing
IEEE Transactions on Software Engineering (accepted)
-
Attack as Detection: Using Adversarial Attack Methods to Detect Abnormal Examples
ACM Transactions on Software Engineering and Methodology (accepted)
-
Boosting Adversarial Training in Safety-critical Systems through Boundary Data Selection
IEEE Robotics and Automation Letters (accepted)
-
K-RAPID: A Formal Executable Semantics of the RAPID Robot Programming Language
10th ACM Cyber-Physical System Security Workshop at AsiaCCS, Singapore, Jul 2024
2023
-
HODOR: Shrinking Attack Surface on Node.js via System Call Limitation
30th ACM Conference on Computer and Communications Security, Copenhagen, Nov 2023
-
K-ST: A Formal Executable Semantics of the Structured Text Language for PLCs
IEEE Transactions on Software Engineering (accepted)
-
FairRec: Fairness Testing for Deep Recommender Systems
32nd International Symposium on Software Testing and Analysis, Seattle, Jul 2023 (first round 12.6% acceptance)
-
TestSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination
ACM Transactions on Software Engineering and Methodology (accepted)
-
Applying Rely-guarantee Reasoning on Concurrent Memory Management and Mailbox in μC/OS-II: A Case Study
28th International Conference on Formal Methods for Industrial Critical Systems, CONFEST 2023, Antwerp, Sep 2023
-
HODOR: Reducing Attack Surface on Node.js via System Call Limitation
Black Hat Europe, London, Dec 2023
-
DeepJudge: A Testing Framework for Copyright Protection of Deep Learning Models
45th International Conference on Software Engineering, demonstrations track, Melbourne, May 2023
-
图像对抗样本检测综述
软件学报(已接收)
2022
-
Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
43rd IEEE Symposium on Security and Privacy, Oakland, May 2022 · paper
-
QuoTe: Quality-oriented Testing for Deep Learning Systems
ACM Transactions on Software Engineering and Methodology (accepted)
-
NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification
44th International Conference on Software Engineering, Pittsburgh, May 2022 (26% acceptance) · paper
-
Which Neural Network Makes More Explainable Decisions? An Approach Towards Measuring Explainability
Automated Software Engineering, 2022
-
Automatic Protocol Reverse-engineering for Industrial Control Systems with Dynamic Taint Analysis
Frontiers of Information Technology & Electronic Engineering, 2022 (spotlight paper)
-
Defending Cyber-physical Systems through Reverse Engineering Based Memory Sanity Check
IEEE Internet of Things Journal (accepted)
-
Repairing Adversarial Texts through Perturbation
16th International Symposium on Theoretical Aspects of Software Engineering, Cluj-Napoca, Jul 2022
2021
-
RobOT: Robustness-Oriented Testing for Deep Learning Systems
43rd International Conference on Software Engineering, Madrid, May 2021 (22% acceptance) · paper
-
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
IEEE Transactions on Software Engineering · paper
-
Attack as Defense: Characterizing Adversarial Examples using Robustness
30th International Symposium on Software Testing and Analysis, Jul 2021 (22% acceptance)
-
Improving Neural Network Verification through Spurious Region Guided Refinement
27th International Conference on Tools and Algorithms for the Construction and Analysis of Systems, ETAPS 2021, Luxembourg, Apr 2021 · paper
-
HRPDF: A Software-Based Heterogeneous Redundant Proactive Defense Framework for Programmable Logic Controller
Journal of Computer Science and Technology (accepted)
-
Adversarial Attacks and Mitigation for Anomaly Detectors of Cyber-Physical Systems
International Journal of Critical Infrastructure Protection (accepted)
2020
-
White-box Fairness Testing through Adversarial Sampling
42nd International Conference on Software Engineering, Seoul, Oct 2020 (20.9% acceptance) · ACM SIGSOFT distinguished paper award · ACM SIGSOFT research highlights · paper
-
Towards Interpreting Recurrent Neural Network through Probabilistic Abstraction
35th IEEE/ACM International Conference on Automated Software Engineering, Melbourne, Sep 2020 (22.5% acceptance)
-
An Empirical Study on the Correlation between Coverage and Robustness for Deep Neural Networks
25th International Conference on Engineering of Complex Computer Systems, Singapore, Oct 2020
2019
-
Adversarial Sample Detection for Deep Neural Networks through Model Mutation Testing
41st International Conference on Software Engineering, Montreal, May 2019 (20.6% acceptance) · paper
2018
-
Automatically 'Verifying' Discrete-Time Complex Systems through Learning, Abstraction and Refinement
IEEE Transactions on Software Engineering (accepted)
-
Towards 'Verifying' a Water Treatment System
22nd International Symposium on Formal Methods, Oxford, Jul 2018 (28% acceptance)
-
Towards Optimal Concolic Testing
40th International Conference on Software Engineering, Gothenburg, May 2018 (20.9% acceptance) · ACM SIGSOFT distinguished paper award
-
Importance Sampling of Interval Markov Chains
48th International Conference on Dependable Systems and Networks, Luxembourg, Nov 2018 (26.7% acceptance)
-
Learning Probabilistic Models for Model Checking: An Evolutionary Approach and an Empirical Study
International Journal on Software Tools for Technology Transfer, 2018
2017
-
Should We Learn Probabilistic Models for Model Checking? A New Approach and an Empirical Study
20th International Conference on Fundamental Approaches to Software Engineering, ETAPS 2017, Uppsala, Apr 2017 (27% acceptance)
-
Improving Probability Estimation through Active Probabilistic Model Learning
19th International Conference on Formal Engineering Methods, Xi'an, Nov 2017
2016
-
Towards Concolic Testing for Hybrid Systems
21st International Symposium on Formal Methods, Cyprus, Nov 2016