Research: I am the founder and CEO of MAIVER（极数景明（上海）智能科技有限公司）, a machine behavior intelligence company based in Shanghai. My long-term goal is to build trustworthy AI in strong adversarial environments. My current focus is governing the actions of AI agents: training models that judge whether an agent’s action is grounded, authorized, aligned with the user’s intent, and safe to execute. My broader research covers adversarial machine learning, LLM and agent security, model privacy and backdoors, and data-driven software security.

Previously: From 2020 to 2025, I led an AI security research team at a national research institute. I received my Ph.D. degree from the University of Electronic Science and Technology of China (UESTC), advised by Prof. Xiaosong Zhang and Prof. Qingxin Zhu, and was a CSC-funded visiting Ph.D. student at UC Santa Barbara (2018–2019).

Openings: MAIVER is hiring Research Scientists, Research Engineers and Research Interns working on agent behavior governance and LLM post-training. Please drop me an email (xlliu [at] maiver dot ai) for more information.

🔥 News

• [2026.10]  🎉 One of our papers won the Best Student Paper Award (Security Track) at Inscrypt 2026!
• [2026.09]  🎉 Two papers have been accepted to Inscrypt 2026!
• [2026.08]  🎉 One paper has been accepted to TSE!
• [2026.07]  🎉 One paper has been accepted to TDSC!
• [2026.07]  🎉 Two papers have been accepted to ACMMM 2026!
• [2026.06]  🎉 One paper has been accepted to 电子学报!
• [2026.06]  🎉 One paper has been accepted to 计算机学报!
• [2026.05]  🎉 One paper has been accepted to ICML 2026!
• [2026.04]  🎉 One paper has been accepted to ACL 2026!
• [2026.03]  🎉 One paper has been accepted to IoTJ!
• [2026.02]  🎉 One paper has been accepted to 电子学报!
• [2025.11]  🎉 Two papers have been accepted to AAAI 2026!

📝 Selected Publications

Top-tier Conferences and Journal articles

Conference

• ACMMM'26 DIFPA: Boosting Adversarial Transferability via Diffusion-based Importance-aware Feature Pyramid Attack.
  Bin Chen, Jia-Li Yin, Zhaozhe Hu, Genna Ba, Xiaolei Liu, Wei Lin, Yuanlong Yu, and Shouling Ji.
  In Proceedings of the 34th ACM International Conference on Multimedia (ACM MM), November, 2026. (CCF-A)
  [Paper] [DOI]
• ACMMM'26 Boosting Cross-Prompt Adversarial Transferability in VLMs via Anchored Dual-Track Prompt Self-Correction.
  Bin Chen, Jia-Li Yin, Zhaozhe Hu, Genna Ba, Wei Lin, Xiaolei Liu, Lichao Su, Yuanlong Yu, and Shouling Ji.
  In Proceedings of the 34th ACM International Conference on Multimedia (ACM MM), November, 2026. (CCF-A)
  [Paper] [DOI]
• ICML'26 MADA-Attack: Transferable Multi-modal Attention Distraction Adversarial Attack against Vision Language Models.
  Zhihan Qin, Jiahao Chen, Chunyi Zhou, Yuwen Pu, Chunqiang Hu, Xiaolei Liu, and Shouling Ji.
  In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), July, 2026. (CCF-A)
  [Paper] [DOI]
• ACL'26 TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense.
  Cheng Liu, Xiaolei Liu, Xingyu Li, Bangzhou Xin, and Kangyi Ding.
  In Findings of the Association for Computational Linguistics: ACL 2026, July, 2026.
  [Paper] [DOI]
• AAAI'26 LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generation.
  Xingyu Li, Xiaolei Liu, Cheng Liu, Yixiao Xu, Kangyi Ding, Bangzhou Xin, and Jia-Li Yin.
  In Proceedings of the 2026 AAAI Conference on Artificial Intelligence (AAAI), January, 2026. (CCF-A)
  [Paper] [DOI]
• AAAI'26 DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning under Domain Skew.
  Zhou Tan, De Li, Bin Chen, Yirui Huang, Duanshu Fang, Jia-Li Yin, Xiaolei Liu, Songze Li, and Shouling Ji.
  In Proceedings of the 2026 AAAI Conference on Artificial Intelligence (AAAI), January, 2026. (CCF-A)
  [Paper] [DOI]
• ACMMM'25 Focus on Generalization: Improving Adversarial Transferability via Bi-Level Bias Mitigation.
  Yiqiang Guo, Lei Zhong, Bin Chen, Jia-Li Yin, Xiaolei Liu, and Shouling Ji.
  In Proceedings of the 33rd ACM International Conference on Multimedia (ACM MM), October, 2025. (CCF-A)
  [Paper] [DOI]
• USENIX Sec'25 MalGuard: Towards Real-Time, Accurate, and Actionable Detection of Malicious Packages in PyPI Ecosystem.
  Xingan Gao, Xiaobing Sun, Sicong Cao, Kaifeng Huang, Du Wu, Xiaolei Liu, Xingwei Lin, and Yang Xiang.
  In Proceedings of the 34th USENIX Security Symposium (USENIX Sec), August, 2025. (CCF-A)
  [Paper] [DOI]
• ICCV'25 KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles.
  Chaoyong Yang, Jia-Li Yin, Bin Chen, Zhaozhe Hu, Xiaolei Liu, and Wei Lin.
  In Proceedings of the 2025 International Conference on Computer Vision (ICCV), October, 2025. (CCF-A)
  [Paper] [DOI]
• CCS'24 SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems.
  Oubo Ma, Yuwen Pu, Linkang Du, Yang Dai, Ruo Wang, Xiaolei Liu, Yingcai Wu, and Shouling Ji.
  In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security (CCS), December, 2024. (CCF-A)
  [Paper] [Slides] [DOI]
• ASE'24 Snopy: Bridging Sample Denoising with Causal Graph Learning for Effective Vulnerability Detection.
  Sicong Cao, Xiaobing Sun, Xiaoxue Wu, David Lo, Lili Bo, Bin Li, Xiaolei Liu, Xingwei Lin, and Wei Liu.
  In Proceedings of the 39th ACM/IEEE International Conference on Automated Software Engineering (ASE), October, 2024. (CCF-A)
  [Paper] [Video] [Code] [DOI]
• ICASSP'23 Sparse Black-Box Inversion Attack with Limited Information.
  Yixiao Xu, Xiaolei Liu, Teng Hu, Bangzhou Xin, and Run Yang.
  In Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), June, 2023. (CCF-B)
  [Paper] [DOI]
• ICME'22 Targeted Anonymization: A Face Image Anonymization Method for Unauthorized Models.
  Kangyi Ding, Teng Hu, Xiaolei Liu, Weina Niu, Yanping Wang, and Xiaosong Zhang.
  In Proceedings of the 2022 IEEE International Conference on Multimedia and Expo (ICME), August, 2022. (CCF-B)
  [Paper] [DOI]
• ICASSP'22 Sparse Adversarial Attack For Video Via Gradient-Based Keyframe Selection.
  Yixiao Xu, Xiaolei Liu, Mingyong Yin, Teng Hu, and Kangyi Ding.
  In Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May, 2022. (CCF-B)
  [Paper] [DOI]
• AAAI'20 Weighted-sampling audio adversarial example attack.
  Xiaolei Liu, Kun Wan, Yufei Ding, Xiaosong Zhang, and Qingxin Zhu.
  In Proceedings of the 2020 AAAI Conference on Artificial Intelligence (AAAI), February, 2020. (CCF-A)
  [Paper] [Website] [DOI]

Journal

• TSE'26 PSFuzzer: A Multi-Party Protocol Fuzzer for Publish/Subscribe Protocols.
  Xiangpu Song, Yingpei Zeng, Xiaofeng Liu, Xiaolei Liu and Shanqing Guo.
  In IEEE Transactions on Software Engineering, 2026. (CCF-A)
  [Paper] [DOI]
• TDSC'26 NEO: Navigating Entropy in Optimized Black-Box Video Adversarial Attacks.
  Xiaolei Liu, Yixiao Xu, Bangzhou Xin, Kangyi Ding, Jia-Li Yin, Shouling Ji and Xiaosong Zhang.
  In IEEE Transactions on Dependable and Secure Computing, 2026. (CCF-A)
  [Paper] [DOI]
• 电子学报'26 循环诱导驱动的多模态大语言模型可用性压力测试方法.
  刘小垒, 李星煜, 陈厅, 张小松.
  In 电子学报, 2026. (中文CCF-A)
  [Paper] [DOI]
• 计算机学报'26 基于鲁棒模型引导的迁移性对抗攻击方法.
  陈斌, 印佳丽, 林巍, 刘小垒, 于元隆, 纪守领.
  In 计算机学报, 2026. (中文CCF-A)
  [Paper] [DOI]
• IoTJ'26 SEADGAT: A Heterogeneous Graph Attention Network with Cross Distillation for Encrypted Traffic Classification.
  Jiazhong Lu, Kun Yu, Yuanyuan Huang, Zhitan Wei, Jiali Yin, Xiaolei Liu.
  In IEEE Internet of Things Journal, 2026. (JCR-Q1)
  [Paper] [DOI]
• 电子学报'26 基于梯度协同与特征融合的加密流量检测.
  卢嘉中, 余坤, 刘小垒, 张小松.
  In 电子学报, 2026. (中文CCF-A)
  [Paper] [DOI]
• 计算机研究与发展'25 大语言模型安全与隐私风险综述.
  姜毅, 杨勇, 印佳丽, 刘小垒, 李吉亮, 王伟, 田有亮, 巫英才, 纪守领.
  In 计算机研究与发展, 2025. (中文CCF-A)
  [Paper] [DOI]
• TIFS'24 Query-Efficient Model Inversion Attacks: An Information Flow View.
  Yixiao Xu, Binxing Fang, Mohan Li, Xiaolei Liu, and Zhihong Tian.
  In IEEE Transactions on Information Forensics and Security, 2024. (CCF-A)
  [Paper] [DOI]
• TIFS'24 Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model.
  Rongke Liu, Dong Wang, Yizhi Ren, Kaitian Guo, Qianqian Qin, and Xiaolei Liu.
  In IEEE Transactions on Information Forensics and Security, 2024. (CCF-A)
  [Paper] [DOI]
• TCSS'24 Backdoor Attack and Defense on Deep Learning: A Survey.
  Yang Bai, Gaojie Xing, Hongyan Wu, Zhihong Rao, Chuan Ma, Shiping Wang, Xiaolei Liu, Yimin Zhou, Jiajia Tang, Kaijun Huang, and Jiale Kang.
  In IEEE Transactions on Computational Social Systems, 2024. (JCR-Q1)
  [Paper] [DOI]
• IEEE Network'24 An Adversarial Example Defense Algorithm for Intelligent Driving.
  Jiazhong Lu, Chenli Wang, Yuanyuan Huang, Kangyi Ding, and Xiaolei Liu.
  In IEEE Network, 2024. (JCR-Q1)
  [Paper] [DOI]
• IPM'21 Transaction-based classification and detection approach for Ethereum smart contract.
  Teng Hu, Xiaolei Liu, Ting Chen, Xiaosong Zhang, Xiaoming Huang, Weina Niu, Jiazhong Lu, Kun Zhou, and Yuan Liu.
  In Information Processing & Management, 2021. (ESI高被引论文, JCR-Q1)
  [Paper] [DOI]
• TITS'21 Compiler-Based Efficient CNN Model Construction for 5G Edge Devices.
  Kun Wan, Xiaolei Liu, Jianyu Yu, Xiaosong Zhang, Xiaojiang Du, and Nadra Guizani.
  In IEEE Transactions on Intelligent Transportation Systems, 2021. (JCR-Q1)
  [Paper] [DOI]
• KBS'21 A low-query black-box adversarial attack based on transferability.
  Kangyi Ding, Xiaolei Liu, Weina Niu, Teng Hu, Yanping Wang, and Xiaosong Zhang.
  In Knowledge-Based Systems, 2021. (JCR-Q1)
  [Paper] [DOI]

🎖 Honors and Awards

• [2024.12] 🏆 四川省高层次人才计划
• [2024.04] 🏆 中国电子学会青年人才托举工程计划
• [2022.11] 🏆 GeekPWN G-Outstanding Winner
• [2018.05] 🏆 China Scholarship Council (CSC) Scholarship
• [2016.11] 🏆 首届国家网络安全奖学金

👨‍💻 Services

• 中国计算机学会网络与系统安全专委会执行委员
• 中国电子学会网络空间安全专委会委员
• 中国图象图形学学会数字媒体取证与安全专委会委员
• 中国系统工程学会网络空间安全与治理专委会委员
• 中国计算机学会第十三届会员代表
• 四川省人工智能行业协会专家委员会专家
• 通信技术期刊执行编委
• 网络空间安全科学学报青年编委
• 信息网络安全青年编委
• 重庆邮电大学学报青年编委