张熙
Professor
Position
Vice Dean, School of Cyberspace Security; Deputy Director, Key Laboratory of Trusted Distributed Computing and Service (Ministry of Education)
Research interests
Cognitive Security, AI Security
About
I am a Professor at Beijing University of Posts and Telecommunications. I received my Ph.D. from the Department of Computer Science, Tsinghua University in 2012, and my B.S. from the School of Computer Science, Harbin Institute of Technology. From 2015 to 2016, I was a visiting scholar at the University of Illinois at Chicago, under the supervision of Prof. Philip S. Yu. My research interests broadly span Data Mining, AI Security, and Computer Architecture.
Email: zhangx@bupt.edu.cn
Google Scholar Profile: https://scholar.google.com/citations?user=6sRtx0cAAAAJ
I am always looking for highly motivated collaborators, including prospective PhD students, postdoctoral researchers, and research interns. Interested candidates are welcome to contact me via email.
Contact
Selected papers (last 5 years)
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
International Conference on Machine Learning, 2026
X-EviProbe: Post-hoc Parameter-free Evidential Uncertainty Quantification for Frozen Graph Neural Networks
International Conference on Machine Learning, 2026
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
Annual Meeting of the Association for Computational Linguistics, 2026
Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026
Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models
IEEE Transactions on Computational Social Systems, 2026
GCE-UQ: Quantifying and Decomposing Uncertainty in Graph Counterfactual Explanations
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2026
Constrained Paraphrase Consistency for LLM Hallucination Detection
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2026
Hallucination Detection via Internal States and Structured Reasoning Consistency in Large Language Models
IEEE International Conference on Acoustics, Speech, and Signal Processing, 2026
MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting
AAAI Conference on Artificial Intelligence (AAAI 2026), 2026
When Reasoning Leaks Membership: Membership Inference Attack on Black-box Large Reasoning Models
The Web Conference (WWW), 2026
TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs
AAAI Conference on Artificial Intelligence, 2026
Discovering new intents via spatio-temporal pseudo-label denoising
Information Processing & Management, 2026
Finefake: A knowledge-enriched dataset for fine-grained multi-domain fake news detection
Information Fusion, 2026
Fact in Fragments: Deconstructing Complex Claims via LLM-based Atomic Fact Extraction and Verification
Expert Systems with Applications, 2026
Beyond Text: Fine-Grained Multi-Modal Fact Verification with Hypergraph Transformers
Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025
Automated Detection of Pre-training Text in Black-box LLMs
International Joint Conference on Artificial Intelligence, 2025
MRR-FV: Unlocking Complex Fact Verification with Multi-hop Retrieval and Reasoning
AAAI Conference on Artificial Intelligence, 2025
Beyond entity alignment: Towards complete knowledge graph alignment via entity-relation synergy
Expert Systems with Applications, 2025
SCCD: A session-based dataset for Chinese cyberbullying detection
International Conference on Computational Linguistics, 2025
Jailbench: A comprehensive chinese security assessment benchmark for large language models
Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2025
Navigating the Black Box: Leveraging LLMs for Effective Text-Level Graph Injection Attacks
DSC, 2025
Multi-Modal Relation Extraction Enhanced by Out-of-Text Visual Information
IEEE Transactions on Audio, Speech and Language Processing, 2025
LapGLP: Approximating Infinite-Layer Graph Convolutions With Laplacian for Federated Recommendation
IEEE TIFS, 2025
Advancing session-based recommendations with Atten-Mixer+: dynamic and adaptive multi-level intent mining
ACM Transactions on Intelligent Systems and Technology, 2025
One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
NeurIPS, 2025
Ghidorah: Towards Robust Multi-Scale Information Diffusion Prediction via Test-Time Training
AAAI, 2025
Knowledge-aware multimodal pre-training for fake news detection
Information Fusion, 2025
Mitigating Social Hazards: Early Detection of Fake News via Diffusion-Guided Propagation Path Generation
Proceedings of the 32nd ACM International Conference on Multimedia, 2024
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
Advances in Neural Information Processing Systems (Spotlight), 2024
GPT4Rec: Graph Prompt Tuning for Streaming Recommendation
Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024
Deeply Fusing Semantics and Interactions for Item Representation Learning via Topology-driven Pre-training
Proceedings of the 32nd ACM International Conference on Multimedia, 2024
Evidence retrieval is almost all you need for fact verification
Findings of the Association for Computational Linguistics, 2024
BaitAttack: Alleviating Intention Shift in Jailbreak Attacks via Adaptive Bait Crafting
EMNLP 2024, 2024
Training for Stable Explanation for Free
NIPS, 2024
Early detection of multimodal fake news via reinforced propagation path generation
IEEE Transactions on Knowledge and Data Engineering, 2024
A survey of text watermarking in the era of large language models
ACM Computing Surveys, 2024
TransGNN: Harnessing the Collaborative Power of Transformers and Graph Neural Networks for Recommender Systems
Proceedings of the 47th International ACM SIGIR conference on research and development in information retrieval, 2024
Collaborative Metapath Enhanced Corporate Default Risk Assessment on Heterogeneous Graph
Proceedings of the ACM Web Conference 2024, 2024
Predicting rumor veracity on social media with cross-channel interaction of multi-task
Neural Computing and Applications, 2024
Improving knowledge distillation for federated learning on non-IID Data
IEEE International Conference on Big Data (BigData), 2023
Don’t Be Misled by Emotion! Disentangle Emotions and Semantics for Cross-Language and Cross-Domain Rumor Detection
IEEE Transactions on Big Data, 2023
Enhanced CGSN System for Machine Reading Comprehension
Natural Language Processing and Chinese Computing, 2023
Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
International Joint Conference on Neural Networks (IJCNN), 2023
Inconsistent Matters: A Knowledge-Guided Dual-Consistency Network for Multi-Modal Rumor Detection
IEEE Transactions on Knowledge and Data Engineering, 2023
Clean-label poisoning attack against fake news detection models
IEEE International Conference on Big Data, 2023
FedValidate: A robust federated learning framework based on client-side validation
International Conference on Data Science in Cyberspace, 2023
Cross-Lingual Propaganda Detection
2022 IEEE International Conference on Big Data (Big Data), 2022
Abusive Language Detection with Graph based Multi-task Learning
2022 IEEE International Conference on Big Data (Big Data), 2022
Predicting Rumor Veracity on Social Media with Graph Structured Multi-task Learning
International Conference on Database Systems for Advanced Applications, 2022
MFAN: Multi-modal feature-enhanced attention networks for rumor detection
International Joint Conference on Artificial Intelligence, 2022