Publications

Authors with underline are my supervised students, and * indicates equal contribution. Full and up-to-date list is on Google Scholar.

Show:

Preprints

2025

  1. Understanding and Rectifying Safety Perception Distortion in VLMs
    Xiaohan Zou, Jian Kang, George Kesidis and Lu Lin
    arXiv preprint arXiv:2502.13095 (arXiv 2025) [Paper]
  2. GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
    Yaopei Zeng, Yuanpu Cao and Lu Lin
    arXiv preprint arXiv:2503.03944 (arXiv 2025) [Paper]
  3. FairCode: Evaluating Social Bias of LLMs in Code Generation
    Yongkang Du, Jen-tse Huang, Jieyu Zhao and Lu Lin
    arXiv preprint arXiv:2501.05396 (arXiv 2025) [Paper]

2024

  1. Mitigating Graph Covariate Shift via Score-based Out-of-distribution Augmentation
    Bohan Wang, Yurui Chang and Lu Lin
    arXiv preprint arXiv:2410.17506 (arXiv 2024) [Paper]
  2. Training a Label-Noise-Resistant GNN with Reduced Complexity
    Rui Zhao, Bin Shi, Zhiming Liang, Jianfei Ruan, Bo Dong and Lu Lin
    arXiv preprint arXiv:2411.11020 (arXiv 2024) [Paper]
  3. Adversarially robust industrial anomaly detection through diffusion model
    Yuanpu Cao, Lu Lin and Jinghui Chen
    arXiv preprint arXiv:2408.04839 (arXiv 2024) [Paper]

Conference & Journal Papers

2025

  1. JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution
    Yurui Chang*, Bochuan Cao*, Yujia Wang, Jinghui Chen and Lu Lin
    Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025) [Paper] [Code]
  2. Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
    Yurui Chang, Bochuan Cao and Lu Lin
    Findings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL Findings 2025) [Paper] [Code]
  3. AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
    Yaopei Zeng, Yuanpu Cao, Bochuan Cao, Yurui Chang, Jinghui Chen and Lu Lin
    Proceedings of the 42nd International Conference on Machine Learning (ICML 2025) [Paper] [Code]
  4. Boosting E-commerce Content Diversity: A Graph-based RAG Approach with User Reviews
    Jiaxi Yang, Yiling Jia, Carl Yang, Yi Liang and Lu Lin
    Proceedings of the 31st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025) [Paper]
  5. WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
    Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin, Prasenjit Mitra and Jinghui Chen
    Findings of the 2025 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL Findings 2025) [Paper]

2024

  1. Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
    Yuanpu Cao, Tianrong Zhang, Bochuan Cao, Ziyi Yin, Lu Lin, Fenglong Ma and Jinghui Chen
    Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024) [Paper] [Code]
  2. Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM
    Bochuan Cao, Yuanpu Cao, Lu Lin and Jinghui Chen
    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2024) [Paper] [Code]
  3. Jailbreak Open-Sourced Large Language Models via Enforced Decoding
    Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu, Bochuan Cao, Lu Lin, Jinyuan Jia, Jinghui Chen and Dinghao Wu
    Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL 2024) [Paper] [Code]
  4. Graph Adversarial Diffusion Convolution
    Songtao Liu, Jinghui Chen, Tianfan Fu, Lu Lin, Marinka Zitnik and Dinghao Wu
    Proceedings of the 41st International Conference on Machine Learning (ICML 2024) [Paper] [Code]
  5. Backdoor Contrastive Learning via Bi-level Trigger Optimization
    Weiyu Sun, Xinyu Zhang, Hao Lu, Ying-Cong Chen, Ting Wang, Jinghui Chen and Lu Lin
    Proceedings of of the 12th International Conference on Learning Representations (ICLR 2024) [Paper] [Code]
  6. Globally Interpretable Graph Learning via Distribution Matching
    Yi Nian*, Yurui Chang*, Wei Jin and Lu Lin
    Proceedings of the Web Conference (WWW 2024) [Paper]
  7. Graph Contrastive Learning via Interventional View Generation
    Zengyi Wo, Minglai Shao, Wenjun Wang, Xuan Guo and Lu Lin
    Proceedings of the Web Conference (WWW 2024) [Paper]

2023

  1. A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
    Hangfan Zhang, Jinyuan Jia, Jinghui Chen, Lu Lin and Dinghao Wu
    Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS 2023) [Paper] [Code]
  2. FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning
    Songtao Liu, Zhengkai Tu, Minkai Xu, Zuobai Zhang, Lu Lin, Rex Ying, Jian Tang, Peilin Zhao and Dinghao Wu
    Proceedings of the 40th International Conference on Machine Learning (ICML 2023) [Paper] [Code]
  3. Graph Contrastive Backdoor Attacks
    Hangfan Zhang, Jinghui Chen, Lu Lin, Jinyuan Jia and Dinghao Wu
    Proceedings of the 40th International Conference on Machine Learning (ICML 2023) [Paper]
  4. Spectral augmentation for self-supervised learning on graphs
    Lu Lin, Jinghui Chen and Hongning Wang
    Proceedings of the 11th International Conference on Learning Representations (ICLR 2023) [Paper] [Code]

2022

  1. Graph Structural Attack by Perturbing Spectral Distance
    Lu Lin, Ethan Blaser and Hongning Wang
    Proceedings of the 28th ACM SIGKDD international conference on knowledge discovery & data mining (KDD 2022) [Paper] [Code]
  2. Communication-Efficient Adaptive Federated Learning
    Yujia Wang, Lu Lin and Jinghui Chen
    Proceedings of the 39th International Conference on Machine Learning (ICML 2022) [Paper]
  3. Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
    Yujia Wang, Lu Lin and Jinghui Chen
    Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022) [Paper]
  4. Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization
    Yujia Wang, Lu Lin and Jinghui Chen
    International Workshop on Trustable, Verifiable and Auditable Federated Learning in Conjunction with AAAI (AAAI Workshop 2022) [Paper]
  5. Unbiased Graph Embedding with Biased Graph Observations
    Nan Wang*, Lu Lin*, Jundong Li and Hongning Wang
    Proceedings of the Web Conference (WWW 2022) [Paper] [Code]
  6. Graph Embedding with Hierarchical Attentive Membership
    Lu Lin, Ethan Blaser and Hongning Wang
    Proceedings of the 15th International Conference on Web Search and Data Mining (WSDM 2022) [Paper]

2020

  1. Graph Attention Networks over Edge Content-based Channels
    Lu Lin and Hongning Wang
    Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining (KDD 2020) [Paper] [Code]
  2. JNET: Learning User Representations via Joint Network Embedding and Topic Embedding
    Lin Gong, Lu Lin, Weihao Song and Hongning Wang
    Proceedings of the 13th International Conference on Web Search and Data Mining (WSDM 2020) [Paper] [Code]

2019

  1. Sequential Learning with Active Partial Labeling for Building Metadata
    Lu Lin, Zheng Luo, Dezhi Hong and Hongning Wang
    Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys 2019) [Paper] [Code]
  2. Learning Personalized Topical Compositions with Item Response Theory
    Lu Lin, Lin Gong and Hongning Wang
    Proceedings of the 12th ACM International Conference on Web Search and Data Mining (WSDM 2019) [Paper]

2017

  1. Road Traffic Speed Prediction: A Probabilistic Model Fusing Multi-source Data
    Lu Lin, Jianxin Li, Feng Chen, Jieping Ye and Jinpeng Huai
    IEEE Transactions on Knowledge and Data Engineering (TKDE 2017) [Paper]

2014

  1. Opinion Mining and Sentiment Analysis in Social Networks: A Retweeting Structure-aware Approach
    Lu Lin, Jianxin Li, Richong Zhang, Weiren Yu and Chenggen Sun
    Proceedings of 7th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2014) [Paper]