Publications

Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game

Published in Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), 2026

Recommended citation: Yuanbo Xie, Yingjie Zhang, Yulin Li, Shouyou Song, Xiaokun Chen, Zhihan Liu, Liya Su, Tingwen Liu. Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Game. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8503-8518, ACL 2026, San Diego, California, United States. https://aclanthology.org/2026.acl-long.385/

Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent

Published in The Computer Journal, 2024, British Computer Society / Oxford University Press, 2024

Download paper here

Recommended citation: Shang Shang, Xinqiang Zhao, Zhongjiang Yao, Yepeng Yao, Liya Su, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang. Can LLMs deeply detect complex malicious queries? A framework for jailbreaking via obfuscating intent. The Computer Journal, 2024. https://doi.org/10.1093/comjnl/bxae124

IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts

Published in European Symposium on Research in Computer Security (ESORICS 2024), LNCS 14985, Springer, 2024

Download paper here

Recommended citation: Shang Shang, Zhongjiang Yao, Yepeng Yao, Liya Su, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang. IntentObfuscator: A Jailbreaking Method via Confusing LLM with Prompts. In J. Garcia-Alfaro et al. (Eds.): ESORICS 2024, LNCS 14985, pp. 146-165, Springer, 2024. https://doi.org/10.1007/978-3-031-70903-6_8

The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks

Published in arXiv, 2023

Download paper here

Recommended citation: Xiaoyi Chen, Siyuan Tang, Rui Zhu, Shijun Yan, Lei Jin, Zihao Wang, Liya Su, XiaoFeng Wang, Haixu Tang. The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks. arXiv 2023. https://arxiv.org/abs/2311.16189

Evil Under the Sun: Understanding and Discovering Attacks on Ethereum Decentralized Applications Evil Under the Sun: Understanding and Discovering Attacks on Ethereum Decentralized Applications

Published in USENIX Security, 2021

Download paper here

Recommended citation: Liya Su, Xinyue Shen, Xiangyu Du, Xiaojing Liao, XiaoFeng Wang, Luyi Xing, Baoxu Liu. Evil Under the Sun: Understanding and Discovering Attacks on Ethereum Decentralized Applications[C]. USENIX Security. 2021 http://academicpages.github.io/files/evil.pdf

Understanding the Influence of Graph Kernels on Deep Learning Architecture: A Case Study of Flow-Based Network Attack Detection Understanding the Influence of Graph Kernels on Deep Learning Architecture: A Case Study of Flow-Based Network Attack Detection

Published in TrustCom/BigDataSE IEEE, 2019

Download paper here

Recommended citation: Liya Su, Yepeng Yao, Zhigang Lu, Baoxu Liu: Understanding the Influence of Graph Kernels on Deep Learning Architecture: A Case Study of Flow-Based Network Attack Detection[C]//2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). IEEE, 2019: 312-318. https://ieeexplore.ieee.org/abstract/document/8887382

STDeepGraph: Spatial-Temporal Deep Learning on Communication Graphs for Long-Term Network Attack Detection STDeepGraph: Spatial-Temporal Deep Learning on Communication Graphs for Long-Term Network Attack Detection

Published in TrustCom/BigDataSE IEEE, 2019

Download paper here

Recommended citation: Yepeng Yao, Liya Su, Zhigang Lu, Baoxu Liu. STDeepGraph: Spatial-Temporal Deep Learning on Communication Graphs for Long-Term Network Attack Detection[C]//2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). IEEE, 2019: 120-127. https://ieeexplore.ieee.org/document/8887381

Marrying Graph Kernel with Deep Neural Network: A Case Study for Network Anomaly Detection Marrying Graph Kernel with Deep Neural Network: A Case Study for Network Anomaly Detection

Published in ICCS Springer, 2019

Download paper here

Recommended citation: Yepeng Yao, Liya Su, Chen Zhang, Zhigang Lu, Baoxu Liu. Marrying Graph Kernel with Deep Neural Network: A Case Study for Network Anomaly Detection[C]//2019 International Conference on Computational Science. Springer, Cham, 2019: 102-115. https://link.springer.com/chapter/10.1007/978-3-030-22741-8_8

A Novel Approach for Identifying Lateral Movement Attacks Based on Network Embedding A Novel Approach for Identifying Lateral Movement Attacks Based on Network Embedding

Published in IEEE International Symposium on Parallel Architectures, Algorithms and Networks (ISPA), 2018

Recommended citation: Mingyi Chen, Yepeng Yao, Junrong Liu, Bo Jiang, Liya Su, Zhigang Lu. A Novel Approach for Identifying Lateral Movement Attacks Based on Network Embedding. ISPA 2018: 708-715.

DeepGFL: Deep Feature Learning via Graph for Attack Detection on Flow-based Network Traffic DeepGFL: Deep Feature Learning via Graph for Attack Detection on Flow-based Network Traffic

Published in Milcom IEEE, 2018

Download paper here

Recommended citation: Yepeng Yao, Liya Su, Zhigang Lu: DeepGFL: Deep Feature Learning via Graph for Attack Detection on Flow-based Network Traffic[C]//2018 Milcom. IEEE, 2018: 579-584. https://ieeexplore.ieee.org/document/8599821

Hierarchical Clustering Based Network Traffic Data Reduction for Improving Suspicious Flow Detection Hierarchical Clustering Based Network Traffic Data Reduction for Improving Suspicious Flow Detection

Published in TrustCom/BigDataSE 2018, 2018

Download paper here

Recommended citation: Liya Su, Yepeng Yao, Ning Li, Junrong Liu, Zhigang Lu, Baoxu Liu. Hierarchical Clustering Based Network Traffic Data Reduction for Improving Suspicious Flow Detection[C]//2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). IEEE, 2018: 744-753. https://ieeexplore.ieee.org/document/8455976

An Improved Method to Unveil Malware’s Hidden Behavior An Improved Method to Unveil Malware’s Hidden Behavior

Published in International Conference on Information Security and Cryptology (Inscrypt), 2017

Recommended citation: Qiang Li, Yunan Zhang, Liya Su, et al. An Improved Method to Unveil Malware’s Hidden Behavior. International Conference on Information Security and Cryptology. Springer, Cham, 2017: 362-382.

Recommended citation: Qiang Li, Yunan Zhang, Liya Su, et al. An Improved Method to Unveil Malware Hidden Behavior. Inscrypt 2017: 362-382.

Suliya

Publications