Yifan Liao, Yuxin Cao, Yedi Zhang, Wentao He, Yan Xiao, Xianglong Du, Zhiyong Huang, Jin Song Dong: Towards Stealthy and Effective Backdoor Attacks on Lane Detection: A Naturalistic Data Poisoning Approach. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2026.
Mengmeng Ma, Ruofan Liu, Yun Lin, Zhiyong Huang, Jin Song Dong: TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable Confidence. International Conference on Learning Representations (ICLR) 2026.
Yuxin Cao, Wei Song, Derui Wang, Jingling Xue, Jin Song Dong: Failures to Surface Harmful Contents in Video Large Language Models. AAAI Conference on Artificial Intelligence (AAAI) 2026.
Tianxi Gao, Yufan Cai, Yusi Yuan, Jin Song Dong: Mapping LLM Capability Frontiers via Formalized and Calibrated Probes. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2026.
Hongtai Wang, Ming Xu, Yanpei Guo, Weili Han, Hoon Wei Lim, Jin Song Dong: RulePilot: An LLM-Powered Agent for Security Rule Generation. IEEE/ACM International Conference on Software Engineering (ICSE) 2026.
Zixiao Zhao, Jing Sun, Zhe Hou, Zhiyuan Wei, Cheng-Hao Cai, Miao Qiao, Jin Song Dong: MaCTG: Multi-Agent Collaborative Thought Graph for Automatic Programming. IEEE/ACM International Conference on Software Engineering (ICSE) 2026.
Wenjie Zhang, Yun Lin, Chun Fung Amos Kwok, Xiwen Teoh, Xiaofei Xie, Frank Liauw, Hongyu Zhang, Jin Song Dong: MINES: Explainable Anomaly Detection through Web API Invariant Inference. IEEE/ACM International Conference on Software Engineering (ICSE) 2026.
Jiayi Hu, Jingling Sun, Chong Wang, Yihao Huang, Jincao Feng, Yilongfei Xu, Yong Li, Kailong Wang, Weikai Miao, Jin Song Dong, Geguang Pu: ADARULE: LLM-Driven Natural Language to LTL Conversion via Pattern-Adaptive Rule Induction. IEEE/ACM International Conference on Software Engineering (ICSE) 2026.
Hongshu Wang, Xinyue Zuo, Yiyang Sun, Qian Li, Yamine Ait Ameur, Jin Song Dong: Towards LLM Agent for Formal Model Synthesis and Fixing. ACM International Conference on the Foundations of Software Engineering (FSE) 2026.
Xiwen Teoh, Yun Lin, Duc-Minh Nguyen, Ruofei Ren, Wenjie Zhang, Jin Song Dong: WebTestPilot: Agentic End-to-End Web Testing against Natural Language Specification by Inferring Oracles with Symbolized GUI Elements. ACM International Conference on the Foundations of Software Engineering (FSE) 2026.
Binhang Qi, Yun Lin, Xinyi Weng, Chenyan Liu, Hailong Sun, Gordon Fraser, Jin Song Dong: Generalizing Test Cases for Comprehensive Test Scenario Coverage. ACM International Conference on the Foundations of Software Engineering (FSE) 2026.
Xianglin Yang, Bryan Hooi, Gelei Deng, Tianwei Zhang, Jin Song Dong: Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges. International Conference on Machine Learning (ICML) 2026.
Xiaoyue Lu, Xianglin Yang, Haijun Liu, Jiahao Liu, Kuntai Cai, Yan Xiao, Jin Song Dong: Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications. Annual Meeting of the Association for Computational Linguistics (ACL) 2026.
Yuan Xiao, Yuchen Chen, Jiaming Wang, Wei Song, Jun Sun, Shiqing Ma, Yanzhou Mu, Juan Zhai, Chunrong Fang, Jin Song Dong, Zhenyu Chen: Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets. Findings of the Association for Computational Linguistics (ACL Findings) 2026.
Ming Xu, Hongtai Wang, Yanpei Guo, Zhengmin Yu, Weili Han, Hoon Wei Lim, Jin Song Dong, Jiaheng Zhang: ARuleCon: Agentic Security Rule Conversion. ACM Web Conference (WWW) 2026.
Xiangxiang Chen, Peixin Zhang, Jun Sun, Jin Song Dong, Wenhai Wang, Jingyi Wang: LLMQuA: Practical Backdoor Injection on Large Language Model Quantization. ACM Web Conference (WWW) 2026.
Ruofan Liu, Yun Lin, Zhiyong Huang, Jin Song Dong: DRIP: Defending Prompt Injection via De-instruction Training and Residual Fusion Model Architecture. ACM Conference on Computer and Communications Security (CCS) 2026.
Yuxin Cao, Kai Ye, Derui Wang, Minhui Xue, Hao Ge, Chenxiong Qian, Jin Song Dong: Bones of Contention: Exploring Query-Efficient Attacks Against Skeleton Recognition Systems. IEEE Transactions on Information Forensics and Security, 2026.
Minghui Meng, Chen Yan, Qian Zhang, Ziming Wang, Kai Wang, Sze Wei Teo, Guangdong Bai, Jin Song Dong: Assessing Privacy Disclosure Compliance of Android Third-Party SDK. IEEE Transactions on Software Engineering, 2026.
Jin Song Dong, Yufan Cai, Zhe Hou, Jing Sun, Hongshu Wang, Yifan Zhang, Xinyue Zuo: Synergizing LLMs and Formal Methods for Neural-Symbolic Reasoning. Communications of the ACM (CACM), 2026.
Yedi Zhang, Yi Sun, Annabelle Lee, Jin Song Dong: RvLLM: LLM Runtime Verification with Domain Knowledge. Advances in Neural Information Processing Systems (NeurIPS) 2025.
Weifei Jin, Yuxin Cao, Junjie Su, Minhui Xue, Jie Hao, Ke Xu, Jin Song Dong, Derui Wang: ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models. Advances in Neural Information Processing Systems (NeurIPS) 2025.
Wanying Dai, Bao Li, Ning Dong, Guangdong Bai, Jin Song Dong: FracFace: Breaking the Visual Clues: Fractal-Based Privacy-Preserving Face Recognition. Advances in Neural Information Processing Systems (NeurIPS) 2025.
Yifan Zhang, Yufan Cai, Xinyue Zuo, Xuan Luan, Kai Wang, Meng Sun, Zhe Hou, Jing Sun, Jin Song Dong: Position: Trustworthy AI Agents Require the Integration of LLM with Formal Methods. International Conference on Machine Learning (ICML) 2025.
Qi Zhou, Tianlin Li, Qing Guo, Dongxia Wang, Yun Lin, Yang Liu, Jin Song Dong: Defending LVLMs Against Vision Attacks through Partial-Perception Supervision. International Conference on Machine Learning (ICML) 2025.
Yufan Cai, Zhe Hou, David Sanan, Xuan Luan, Yun Lin, Jing Sun, Jin Song Dong: Automated Program Refinement: Guide and Verify Code Large Language Model with Refinement Calculus. ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL) 2025.
Xinyue Zuo, Yifan Zhang, Hongshu Wang, Yufan Cai, Zhe Hou, Jing Sun, Jin Song Dong: PAT-Agent: Autoformalization for Model Checking. IEEE/ACM International Conference on Automated Software Engineering (ASE) 2025.
Weifei Jin, Yuxin Cao, Junjie Su, Derui Wang, Yedi Zhang, Minhui Xue, Jie Hao, Jin Song Dong, Yixian Yang: Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems. USENIX Security Symposium 2025.
Xiwen Teoh, Yun Lin, Siqi Li, Ruofan Liu, Avi Sollomoni, Yaniv Harel, Jin Song Dong: Are CAPTCHAs Still Bot-hard? Generalized Visual CAPTCHA Solving with Agentic Vision Language Model. USENIX Security Symposium 2025.
Rajdeep Singh Hundal, Yan Xiao, Xiaochun Cao, Jin Song Dong, Manuel Rigger: On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations. IEEE/ACM International Conference on Software Engineering (ICSE) 2025.
Yedi Zhang, Lei Huang, Pengfei Gao, Fu Song, Jun Sun, Jin Song Dong: Verification of Bit-Flip Attacks against Quantized Neural Networks. ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages, and Applications (OOPSLA) 2025.
Jinhao Dong, Jun Sun, Wenjie Zhang, Jin Song Dong, Dan Hao: ConTested: Consistency-Aided Tested Code Generation with LLM. International Symposium on Software Testing and Analysis (ISSTA) 2025.
Ruofan Liu, Xiwen Teoh, Yun Lin, Denys Poshyvanyk, Jin Song Dong: GUIPilot: A Consistency-based Mobile GUI Testing Approach for Detecting Application-specific Bugs. International Symposium on Software Testing and Analysis (ISSTA) 2025.
Xinyue Zuo, Yan Xiao, Xiaochun Cao, Wenhai Wang, Jin Song Dong: DT4LM: Differential Testing for Reliable Language Model Updates in Classification Tasks. IEEE Transactions on Software Engineering, 2025.
Hongyu Zhang, Dengfeng Han, Shanshan Zhuang, Ziming Wang, Jun Sun, Yulei Liu, Jin Liu, Jin Song Dong: Explainable and Transferable Adversarial Attack for ML-based Network Intrusion Detectors. IEEE Transactions on Dependable and Secure Computing, 2025.
Yan Xiao, Xinyue Zuo, Xiaochun Cao, Jin Song Dong, Ivan Beschastnikh: Promises and Perils of Using Transformer-based Models for SE Research. Neural Networks, 2025.
Yedi Zhang, Guangke Chen, Fu Song, Jun Sun, Jin Song Dong: Certified Quantization Strategy Synthesis for Neural Networks. International Symposium on Formal Methods (FM) 2024.
Ruofan Liu, Yun Lin, Xiwen Teoh, Zhiyong Huang, Jin Song Dong: Less Defined Knowledge and More True Alarms: Reference-based Phishing Detection without a Pre-defined Reference List. USENIX Security Symposium 2024.
Xiwen Teoh, Yun Lin, Ruofan Liu, Zhiyong Huang, Jin Song Dong: PhishDecloaker: Detecting CAPTCHA-cloaked Phishing Websites via Hybrid Vision-based Interactive Models. USENIX Security Symposium 2024.
Yudai Pan, Jun Liu, Tianzhe Zhao, Lingling Zhang, Yun Lin, Jin Song Dong: A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction. ACM Web Conference (WWW) 2024.
Xianglin Yang, Yun Lin, Yifan Zhang, Linpeng Huang, Jin Song Dong, Hong Mei: DeepDebugger: An Interactive Time-Travelling Debugging Approach for Deep Classifiers. ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) 2023.
Gelin Zhang, Zhe Hou, Yanhong Huang, Jianqi Shi, Hadrien Bride, Jin Song Dong, Yongsheng Gao: Extracting Optimal Explanations for Ensemble Trees via Automated Reasoning. Applied Intelligence, 2023.
Jihong Wang, Minnan Luo, Jundong Li, Yun Lin, Yuxiao Dong, Jin Song Dong, Quanshi Zheng: Empower Post-hoc Graph Explanations with Information Bottleneck: A Pre-training and Fine-tuning Perspective. ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023.
Ruofan Liu, Yun Lin, Yifan Zhang, Pei Lee, Jin Song Dong: Knowledge Expansion and Counterfactual Interaction for Reference-Based Phishing Detection. USENIX Security Symposium 2023.