Yi Liu

Employment

Employment history is unavailable.

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (20)

• Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment
  2027 DOI: 10.1007/978-3-032-31583-0_5
  +Save
• How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study
  2026 DOI: 10.1145/3832783.3834373
  +Save
• SAF: An AI-Agent-Ready and Browser-Accessible Static Analysis Framework for LLVM IR
  2026 DOI: 10.1145/3832783.3834597
  +Save
• SPOLRE: Semantic Preserving Object Layout Reconstruction for Image Captioning System Testing
  ACM Transactions on Software Engineering and Methodology 2026 DOI: 10.1145/3748306
  +Save
• Oedipus: LLM-enchanced Reasoning CAPTCHA Solver
  2025 DOI: 10.1145/3719027.3744872
  +Save
• MiniScope : Automated UI Exploration and Privacy Inconsistency Detection of MiniApps via Two-phase Iterative Hybrid Analysis
  ACM Transactions on Software Engineering and Methodology 2025 DOI: 10.1145/3709351
  +Save
• IllusionCAPTCHA: A CAPTCHA based on Visual Illusion
  2025 DOI: 10.1145/3696410.3714726
  +Save
• Efficient Detection of Toxic Prompts in Large Language Models
  2024 DOI: 10.1145/3691620.3695018
  +Save
• Drowzee: Metamorphic Testing for Fact-Conflicting Hallucination Detection in Large Language Models
  Proceedings of the ACM on Programming Languages 2024 DOI: 10.1145/3689776
  +Save
• DistillSeq: A Framework for Safety Alignment Testing in Large Language Models using Knowledge Distillation
  2024 DOI: 10.1145/3650212.3680304
  +Save
• A Hitchhiker’s Guide to Jailbreaking ChatGPT via Prompt Engineering
  2024 DOI: 10.1145/3663530.3665021
  +Save
• Glitch Tokens in Large Language Models: Categorization Taxonomy and Effective Detection
  Proceedings of the ACM on Software Engineering 2024 DOI: 10.1145/3660799
  +Save
• Medusa: Unveil Memory Exhaustion DoS Vulnerabilities in Protocol Implementations
  2024 DOI: 10.1145/3589334.3645476
  +Save
• MeTMaP: Metamorphic Testing for Detecting False Vector Matching Problems in LLM Augmented Generation
  2024 DOI: 10.1145/3650105.3652297
  +Save
• RESTCluster: Automated Crash Clustering for RESTful API
  2022 DOI: 10.1145/3551349.3559511
  +Save
• Morest: model-based RESTful API testing with execution feedback
  Proceedings of the 44th International Conference on Software Engineering 2022 DOI: 10.1145/3510003.3510133
  +Save
• Automatic Web Testing Using Curiosity-Driven Reinforcement Learning
  2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE) 2021 DOI: 10.1109/icse43902.2021.00048
  +Save
• Industry practice of Javascript dynamic analysis on WeChat mini-programs
  Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering 2020 DOI: 10.1145/3324884.3421842
  +Save
• An Exploratory Study of Bugs in Extended Reality Applications on the Web
  2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE) 2020 DOI: 10.1109/issre5003.2020.00025
  +Save
• JSOptimizer: An Extensible Framework for JavaScript Program Optimization
  2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) 2019 DOI: 10.1109/icse-companion.2019.00069
  +Save