Zongru Wu

27 papers A* 1B 1Journal 21Unranked 4
YearRankTypeTitle / Venue / Authors
2026 A* conf
GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents.
AAAI
Zheng Wu, Pengzhou Cheng, Zongru Wu, Lingzhong Dong, Zhuosheng Zhang
2026 J jnl
ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data.
CoRR
Haodong Zhao, Jinming Hu, Zhaomin Wu, Zongru Wu, Wei Du, Junyi Hou, Caibei Zhao, Zhuosheng Zhang, Bingsheng He, Gongshen Liu
2025 J jnl
Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations.
CoRR
Pengzhou Cheng, Lingzhong Dong, Zeng Wu, Zongru Wu, Xiangru Tang, Chengwei Qin, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review.
IEEE Trans. Neural Networks Learn. Syst.
Pengzhou Cheng, Zongru Wu, Wei Du, Haodong Zhao, Wei Lu, Gongshen Liu
2025 J jnl
GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents.
CoRR
Zheng Wu, Pengzhou Cheng, Zongru Wu, Lingzhong Dong, Zhuosheng Zhang
2025 B conf
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining.
COLING
Zongru Wu, Pengzhou Cheng, Lingyong Fang, Zhuosheng Zhang, Gongshen Liu
2025 — conf
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents.
EMNLP (Findings)
Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Daizong Ding, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents.
CoRR
Pengzhou Cheng, Haowen Hu, Zheng Wu, Zongru Wu, Tianjie Ju, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Investigating the Adaptive Robustness with Knowledge Conflicts in LLM-based Multi-Agent Systems.
CoRR
Tianjie Ju, Bowen Wang, Hao Fei, Mong-Li Lee, Wynne Hsu, Yun Li, Qianren Wang, Pengzhou Cheng, Zongru Wu, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
MKF-ADS: Multi-Knowledge Fusion Based Anomaly Detection System in Vehicular Control Area Networks.
IEEE Trans. Veh. Technol.
Pengzhou Cheng, Shouxuan Liu, Zongru Wu, Lixing Tan, Gongshen Liu
2025 — conf
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents.
ACL (Findings)
Pengzhou Cheng, Zheng Wu, Zongru Wu, Tianjie Ju, Aston Zhang, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents.
CoRR
Pengzhou Cheng, Zheng Wu, Zongru Wu, Aston Zhang, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
On the Adaptive Psychological Persuasion of Large Language Models.
CoRR
Tianjie Ju, Yujia Chen, Hao Fei, Mong-Li Lee, Wynne Hsu, Pengzhou Cheng, Zongru Wu, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents.
CoRR
Lingzhong Dong, Ziqi Zhou, Shuaibo Yang, Haiyue Sheng, Pengzhou Cheng, Zongru Wu, Zheng Wu, Gongshen Liu, Zhuosheng Zhang
2025 J jnl
See, Think, Act: Teaching Multimodal Agents to Effectively Interact with GUI by Identifying Toggles.
CoRR
Zongru Wu, Rui Mao, Zhiyuan Tian, Pengzhou Cheng, Tianjie Ju, Zheng Wu, Lingzhong Dong, Haiyue Sheng, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks.
CoRR
Zongru Wu, Pengzhou Cheng, Zheng Wu, Tianjie Ju, Zhuosheng Zhang, Gongshen Liu
2025 — conf
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer.
NAACL (Findings)
Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Zhuosheng Zhang, Gongshen Liu
2025 J jnl
Transferable and Robust Dynamic Adversarial Attack Against Object Detection Models.
IEEE Internet Things J.
Xinxin Wang, Jing Chen, Zijun Zhang, Kun He, Zongru Wu, Ruiying Du, Qiao Li, Gongshen Liu
2025 J jnl
VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents.
CoRR
Zheng Wu, Heyuan Huang, Xingyu Lou, Xiangmou Qu, Pengzhou Cheng, Zongru Wu, Weiwen Liu, Weinan Zhang, Jun Wang, Zhaoxiang Wang, Zhuosheng Zhang
2024 — conf
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space.
ACL (1)
Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu
2024 J jnl
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space.
CoRR
Zongru Wu, Zhuosheng Zhang, Pengzhou Cheng, Gongshen Liu
2024 J jnl
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining.
CoRR
Zongru Wu, Pengzhou Cheng, Lingyong Fang, Zhuosheng Zhang, Gongshen Liu
2024 J jnl
MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network.
CoRR
Pengzhou Cheng, Zongru Wu, Gongshen Liu
2024 J jnl
Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models.
CoRR
Pengzhou Cheng, Wei Du, Zongru Wu, Fengwei Zhang, Libo Chen, Gongshen Liu
2024 J jnl
Transferring Backdoors between Large Language Models by Knowledge Distillation.
CoRR
Pengzhou Cheng, Zongru Wu, Tianjie Ju, Wei Du, Zhuosheng Zhang, Gongshen Liu
2024 J jnl
TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models.
CoRR
Pengzhou Cheng, Yidong Ding, Tianjie Ju, Zongru Wu, Wei Du, Ping Yi, Zhuosheng Zhang, Gongshen Liu
2023 J jnl
Backdoor Attacks and Countermeasures in Natural Language Processing Models: A Comprehensive Security Review.
CoRR
Pengzhou Cheng, Zongru Wu, Wei Du, Haodong Zhao, Gongshen Liu