Juan Zhai

91 papers A* 19A 4C 5Misc 1Journal 50Unranked 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
An Empirical Study of Bugs in Modern LLM Agent Frameworks.
CoRR
Xinxue Zhu, Jiacong Wu, Xiaoyu Zhang, Tianlin Li, Yanzhou Mu, Juan Zhai, Chao Shen, Chunrong Fang, Yang Liu
2026 J jnl
Deep Learning Framework Testing via Model Mutation: How Far Are We?
IEEE Trans. Software Eng.
Yanzhou Mu, Rong Wang, Juan Zhai, Chunrong Fang, Xiang Chen, Peiran Yang, Zhixiang Cao, Ruixiang Qian, Shaoyu Yang, Zhenyu Chen
2026 A* conf
From Chaos to Clarity: A Knowledge Graph-Driven Audit Dataset Generation Framework for LLM Unlearning.
AAAI
Weipeng Jiang, Juan Zhai, Shiqing Ma, Ziyan Lei, Xiaofei Xie, Yige Wang, Chao Shen
2026 J jnl
Small Symbols, Big Risks: Exploring Emoticon Semantic Confusion in Large Language Models.
CoRR
Weipeng Jiang, Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Yang Liu
2025 J jnl
ASSURE: Metamorphic Testing for AI-powered Browser Extensions.
CoRR
Xuanqi Gao, Juan Zhai, Shiqing Ma, Siyi Xie, Chao Shen
2025 J jnl
An Automated Monitoring and Repairing System for DNN Training.
IEEE Trans. Dependable Secur. Comput.
Xiaoyu Zhang, Chao Shen, Shiqing Ma, Juan Zhai, Chenhao Lin
2025 — conf
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.
NAACL (Findings)
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
2025 J jnl
Breaking the Myth: Can Small Models Infer Postconditions Too?
CoRR
Gehao Zhang, Zhenting Wang, Juan Zhai
2025 J jnl
DREAM: Debugging and Repairing AutoML Pipelines.
ACM Trans. Softw. Eng. Methodol.
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Xiaohong Guan, Chao Shen
2025 — conf
Data-centric NLP Backdoor Defense from the Lens of Memorization.
NAACL (Findings)
Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma
2025 J jnl
Deep Learning Framework Testing via Heuristic Guidance Based on Multiple Model Measurements.
CoRR
Yinglong Zou, Juan Zhai, Chunrong Fang, Yanzhou Mu, Jiawei Liu, Zhenyu Chen
2025 J jnl
Deep Learning Framework Testing via Model Mutation: How Far Are We?
CoRR
Yanzhou Mu, Rong Wang, Juan Zhai, Chunrong Fang, Xiang Chen, Zhiyuan Peng, Peiran Yang, Ruixiang Qian, Shaoyu Yang, Zhenyu Chen
2025 J jnl
Designing Deep Learning Frameworks for LLMs:Challenges, Expectations, and Opportunities.
CoRR
Yanzhou Mu, Rong Wang, Juan Zhai, Chunrong Fang, Xiang Chen, Jiacong Wu, An Guo, Jiawei Shen, Bingzhuo Li, Zhenyu Chen
2025 J jnl
DevMuT: Testing Deep Learning Framework via Developer Expertise-Based Mutation.
CoRR
Yanzhou Mu, Juan Zhai, Chunrong Fang, Xiang Chen, Zhixiang Cao, Peiran Yang, Yinglong Zou, Tao Zheng, Zhenyu Chen
2025 J jnl
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice.
CoRR
Gehao Zhang, Eugene Bagdasarian, Juan Zhai, Shiqing Ma
2025 J jnl
EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models.
CoRR
Mingzhe Li, Gehao Zhang, Zhenting Wang, Shiqing Ma, Siqi Pan, Richard Cartwright, Juan Zhai
2025 J jnl
GPU Temperature Simulation-Based Testing for In-Vehicle Deep Learning Frameworks.
CoRR
Yinglong Zou, Juan Zhai, Chunrong Fang, Zhenyu Chen
2025 J jnl
Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal.
CoRR
Weipeng Jiang, Juan Zhai, Shiqing Ma, Ziyan Lei, Xiaofei Xie, Yige Wang, Chao Shen
2025 J jnl
Improving Deep Learning Framework Testing with Model-Level Metamorphic Testing.
CoRR
Yanzhou Mu, Juan Zhai, Chunrong Fang, Xiang Chen, Zhixiang Cao, Peiran Yang, Kexin Zhao, An Guo, Zhenyu Chen
2025 J jnl
Improving Deep Learning Framework Testing with Model-Level Metamorphic Testing.
Proc. ACM Softw. Eng.
Yanzhou Mu, Juan Zhai, Chunrong Fang, Xiang Chen, Zhixiang Cao, Peiran Yang, Kexin Zhao, An Guo, Zhenyu Chen
2025 J jnl
LLMCup: Ranking-Enhanced Comment Updating with LLMs.
CoRR
Hua Ge, Juan Zhai, Minxue Pan, Fusen He, Ziyue Tan
2025 J jnl
MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models.
CoRR
Xuanqi Gao, Siyi Xie, Juan Zhai, Shqing Ma, Chao Shen
2025 J jnl
Machine Learning for Actionable Warning Identification: A Comprehensive Survey.
ACM Comput. Surv.
Xiuting Ge, Chunrong Fang, Xuanye Li, Weisong Sun, Daoyuan Wu, Juan Zhai, Shang-Wei Lin, Zhihong Zhao, Yang Liu, Zhenyu Chen
2025 J jnl
Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only.
CoRR
Xuanqi Gao, Weipeng Jiang, Juan Zhai, Shiqing Ma, Siyi Xie, Xinyang Yin, Chao Shen
2025 J jnl
PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization.
CoRR
Mingzhe Li, Renhao Zhang, Zhiyang Wen, Siqi Pan, Bruno Castro da Silva, Juan Zhai, Shiqing Ma
2025 J jnl
Rethinking Technology Stack Selection with AI Coding Proficiency.
CoRR
Xiaoyu Zhang, Weipeng Jiang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Chenhao Lin, Chao Shen, Tianlin Li, Yang Liu
2025 A* conf
STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning.
ICLR
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Tianlin Li, Weipeng Jiang, Yang Liu
2025 J jnl
Scalpel: Automotive Deep Learning Framework Testing via Assembling Model Components.
CoRR
Yinglong Zou, Juan Zhai, Chunrong Fang, An Guo, Jiawei Liu, Zhenyu Chen
2025 — conf
The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation.
ACL (1)
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Qian Wang, Chao Shen, Yang Liu
2025 J jnl
Unveiling Provider Bias in Large Language Models for Code Generation.
CoRR
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Chao Shen, Yang Liu
2024 J jnl
Beyond Code Generation: Assessing Code LLM Maturity with Postconditions.
CoRR
Fusen He, Juan Zhai, Minxue Pan
2024 J jnl
CITADEL: Context Similarity Based Deep Learning Framework Bug Finding.
CoRR
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Shiwei Wang, Chao Shen
2024 J jnl
COSTELLO: Contrastive Testing for Embedding-Based Large Language Model as a Service Embeddings.
Proc. ACM Softw. Eng.
Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
2024 J jnl
DREAM: Debugging and Repairing AutoML Pipelines.
CoRR
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen
2024 J jnl
Data-centric NLP Backdoor Defense from the Lens of Memorization.
CoRR
Zhenting Wang, Zhizhi Wang, Mingyu Jin, Mengnan Du, Juan Zhai, Shiqing Ma
2024 A* conf
DevMuT: Testing Deep Learning Framework via Developer Expertise-Based Mutation.
ASE
Yanzhou Mu, Juan Zhai, Chunrong Fang, Xiang Chen, Zhixiang Cao, Peiran Yang, Yinglong Zou, Tao Zheng, Zhenyu Chen
2024 A conf
Efficient DNN-Powered Software with Fair Sparse Models.
ISSTA
Xuanqi Gao, Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
2024 J jnl
Efficient DNN-Powered Software with Fair Sparse Models.
CoRR
Xuanqi Gao, Weipeng Jiang, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
2024 J jnl
From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions.
CoRR
Weipeng Jiang, Xuanqi Gao, Juan Zhai, Shiqing Ma, Xiaoyu Zhang, Chao Shen
2024 J jnl
Machine Translation Testing via Syntactic Tree Pruning.
CoRR
Quanjun Zhang, Juan Zhai, Chunrong Fang, Jiawei Liu, Weisong Sun, Haichuan Hu, Qingyu Wang
2024 J jnl
Machine Translation Testing via Syntactic Tree Pruning.
ACM Trans. Softw. Eng. Methodol.
Quanjun Zhang, Juan Zhai, Chunrong Fang, Jiawei Liu, Weisong Sun, Haichuan Hu, Qingyu Wang
2024 — conf
Merlin: Multi-tier Optimization of eBPF Code for Performance and Compactness.
ASPLOS (3)
Jinsong Mao, Hailun Ding, Juan Zhai, Shiqing Ma
2024 A* conf
Mutation-Based Deep Learning Framework Testing Method in JavaScript Environment.
ASE
Yinglong Zou, Juan Zhai, Chunrong Fang, Jiawei Liu, Tao Zheng, Zhenyu Chen
2024 J jnl
Mutation-Based Deep Learning Framework Testing Method in JavaScript Environment.
CoRR
Yinglong Zou, Juan Zhai, Chunrong Fang, Jiawei Liu, Tao Zheng, Zhenyu Chen
2024 J jnl
SmartAxe: Detecting Cross-Chain Vulnerabilities in Bridge Smart Contracts via Fine-Grained Static Analysis.
CoRR
Zeqin Liao, Yuhong Nan, Henglong Liang, Sicheng Hao, Juan Zhai, Jiajing Wu, Zibin Zheng
2024 J jnl
SmartAxe: Detecting Cross-Chain Vulnerabilities in Bridge Smart Contracts via Fine-Grained Static Analysis.
Proc. ACM Softw. Eng.
Zeqin Liao, Yuhong Nan, Henglong Liang, Sicheng Hao, Juan Zhai, Jiajing Wu, Zibin Zheng
2024 J jnl
Speculative Coreset Selection for Task-Specific Fine-tuning.
CoRR
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Tianlin Li, Weipeng Jiang, Yang Liu
2024 A* conf
Towards General Robustness Verification of MaxPool-Based Convolutional Neural Networks via Tightening Linear Approximation.
CVPR
Yuan Xiao, Shiqing Ma, Juan Zhai, Chunrong Fang, Jinyuan Jia, Zhenyu Chen
2024 J jnl
Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation.
CoRR
Yuan Xiao, Shiqing Ma, Juan Zhai, Chunrong Fang, Jinyuan Jia, Zhenyu Chen
2024 J jnl
Understanding Privacy Risks of Intelligent Connected Vehicles Through Their Companion Mobile Apps.
IEEE Internet Things J.
Peifu Yang, Yuhong Nan, Lei Xue, Yuliang Zhang, Juan Zhai, Zibin Zheng
2024 J jnl
Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer.
CoRR
Weipeng Jiang, Zhenting Wang, Juan Zhai, Shiqing Ma, Zhengyu Zhao, Chao Shen
2023 J jnl
A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair.
CoRR
Quanjun Zhang, Tongke Zhang, Juan Zhai, Chunrong Fang, Bowen Yu, Weisong Sun, Zhenyu Chen
2023 A* conf
AIRTAG: Towards Automated Attack Investigation by Unsupervised Learning with Log Texts.
USENIX Security Symposium
Hailun Ding, Juan Zhai, Yuhong Nan, Shiqing Ma
2023 A conf
CILIATE: Towards Fairer Class-Based Incremental Learning by Dataset and Training Refinement.
ISSTA
Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Shiwei Wang
2023 J jnl
CILIATE: Towards Fairer Class-based Incremental Learning by Dataset and Training Refinement.
CoRR
Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Shiwei Wang
2023 J jnl
Machine Learning for Actionable Warning Identification: A Comprehensive Survey.
CoRR
Xiuting Ge, Chunrong Fang, Xuanye Li, Weisong Sun, Daoyuan Wu, Juan Zhai, Shangwei Lin, Zhihong Zhao, Yang Liu, Zhenyu Chen
2023 A* conf
The Case for Learned Provenance Graph Storage Systems.
USENIX Security Symposium
Hailun Ding, Juan Zhai, Dong Deng, Shiqing Ma
2023 A* conf
UNICORN: A Unified Backdoor Trigger Inversion Framework.
ICLR
Zhenting Wang, Kai Mei, Juan Zhai, Shiqing Ma
2023 J jnl
UNICORN: A Unified Backdoor Trigger Inversion Framework.
CoRR
Zhenting Wang, Kai Mei, Juan Zhai, Shiqing Ma
2022 A* conf
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning.
CVPR
Zhenting Wang, Juan Zhai, Shiqing Ma
2022 J jnl
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning.
CoRR
Zhenting Wang, Juan Zhai, Shiqing Ma
2022 J jnl
FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons.
CoRR
Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Qian Wang
2022 A* conf
Fairneuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons.
ICSE
Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Qian Wang
2022 J jnl
Neural Network Trojans Analysis and Mitigation from the Input Domain.
CoRR
Zhenting Wang, Hailun Ding, Juan Zhai, Shiqing Ma
2022 A* conf
Rethinking the Reverse-engineering of Trojan Triggers.
NeurIPS
Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai, Shiqing Ma
2022 J jnl
Rethinking the Reverse-engineering of Trojan Triggers.
CoRR
Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai, Shiqing Ma
2022 A* conf
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training.
NeurIPS
Zhenting Wang, Hailun Ding, Juan Zhai, Shiqing Ma
2021 A* conf
AUTOTRAINER: An Automatic DNN Training Problem Detection and Repair System.
ICSE
Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen
2021 A* conf
ELISE: A Storage Efficient Logging System Powered by Redundancy Reduction and Representation Learning.
USENIX Security Symposium
Hailun Ding, Shenao Yan, Juan Zhai, Shiqing Ma
2020 A conf
Automated Generation of LTL Specifications For Smart Home IoT Using Natural Language.
DATE
Shiyu Zhang, Juan Zhai, Lei Bu, Mingsong Chen, Linzhang Wang, Xuandong Li
2020 — conf
C2S: translating natural language comments to formal program specifications.
ESEC/SIGSOFT FSE
Juan Zhai, Yu Shi, Minxue Pan, Guian Zhou, Yongxiang Liu, Chunrong Fang, Shiqing Ma, Lin Tan, Xiangyu Zhang
2020 A* conf
CPC: automatically classifying and propagating natural language comments via program analysis.
ICSE
Juan Zhai, Xiangzhe Xu, Yu Shi, Guanhong Tao, Minxue Pan, Shiqing Ma, Lei Xu, Weifeng Zhang, Lin Tan, Xiangyu Zhang
2020 — conf
Correlations between deep neural network model coverage criteria and model quality.
ESEC/SIGSOFT FSE
Shenao Yan, Guanhong Tao, Xuwei Liu, Juan Zhai, Shiqing Ma, Lei Xu, Xiangyu Zhang
2020 J jnl
Effective testing of Android apps using extended IFML models.
J. Syst. Softw.
Minxue Pan, Yifei Lu, Yu Pei, Tian Zhang, Juan Zhai, Xuandong Li
2020 A conf
FineLock: automatically refactoring coarse-grained locks into fine-grained locks.
ISSTA
Yang Zhang, Shuai Shao, Juan Zhai, Shiqing Ma
2019 — conf
Extracting Mapping Relations for Mobile User Interface Transformation.
Internetware
Ruihua Ji, Junyu Pei, Wenhua Yang, Juan Zhai, Minxue Pan, Tian Zhang
2019 — conf
Preference-wise testing for Android applications.
ESEC/SIGSOFT FSE
Yifei Lu, Minxue Pan, Juan Zhai, Tian Zhang, Xuandong Li
2018 A* conf
Dual-force: understanding WebView malware via cross-language forced execution.
ASE
Zhenhao Tang, Juan Zhai, Minxue Pan, Yousra Aafer, Shiqing Ma, Xiangyu Zhang, Jianhua Zhao
2018 — conf
Kernel-Supported Cost-Effective Audit Logging for Causality Tracking.
USENIX ATC
Shiqing Ma, Juan Zhai, Yonghwi Kwon, Kyu Hyung Lee, Xiangyu Zhang, Gabriela F. Ciocarlie, Ashish Gehani, Vinod Yegneswaran, Dongyan Xu, Somesh Jha
2018 A* conf
Trojaning Attack on Neural Networks.
NDSS
Yingqi Liu, Shiqing Ma, Yousra Aafer, Wen-Chuan Lee, Juan Zhai, Weihang Wang, Xiangyu Zhang
2017 C conf
A Framework for Array Invariants Synthesis in Induction-Loop Programs.
APSEC
Bin Li, Juan Zhai, Zhenhao Tang, Enyi Tang, Jianhua Zhao
2017 C conf
Are Your Classes Well-Encapsulated? Encapsulation Analysis for Java.
QRS
Zhenhao Tang, Juan Zhai, Bin Li, Jianhua Zhao
2017 — conf
LAMP: data provenance for graph based machine learning algorithms through derivative computation.
ESEC/SIGSOFT FSE
Shiqing Ma, Yousra Aafer, Zhaogui Xu, Wen-Chuan Lee, Juan Zhai, Yingqi Liu, Xiangyu Zhang
2017 A* conf
MPI: Multiple Perspective Attack Investigation with Semantic Aware Execution Partitioning.
USENIX Security Symposium
Shiqing Ma, Juan Zhai, Fei Wang, Kyu Hyung Lee, Xiangyu Zhang, Dongyan Xu
2016 C conf
Automatic Invariant Synthesis for Arrays in Simple Programs.
QRS
Bin Li, Zhenhao Tang, Juan Zhai, Jianhua Zhao
2016 A* conf
Automatic model generation from documentation for Java API functions.
ICSE
Juan Zhai, Jianjun Huang, Shiqing Ma, Xiangyu Zhang, Lin Tan, Jianhua Zhao, Feng Qin
2016 C conf
Precondition Calculation for Loops Iterating over Data Structures.
QRS
Juan Zhai, Bin Li, Zhenhao Tang, Jianhua Zhao, Xuandong Li
2015 — conf
Analyzing Inductively Defined Properties for Recursive Data Structures.
Internetware
Zhenhao Tang, Hanfei Wang, Bin Li, Juan Zhai, Jianhua Zhao, Xuandong Li
2015 Misc conf
Assertion-Directed Precondition Synthesis for Loops over Data Structures.
SETTA
Juan Zhai, Hanfei Wang, Jianhua Zhao
2015 C conf
Node-Set Analysis for Linked Recursive Data Structures.
QRS
Zhenhao Tang, Hanfei Wang, Bin Li, Juan Zhai, Jianhua Zhao, Xuandong Li
2014 — conf
Post-condition-Directed Invariant Inference for Loops over Data Structures.
SERE (Companion)
Juan Zhai, Hanfei Wang, Jianhua Zhao