Publications

2027

1. S&P

   Can We Trust LLM Security Research? A Reproducibility Study of Large Language Model Security Papers in Tier-1 Security Conference

   Zeyuan Chen, Ye Leng, Chi Cui, Mengfei Liang, Bo Shao, Xinyu Zhang, Yun Shen, Michael Backes, Xinyue Shen, and Yang Zhang

   In Proceedings of the 2027 IEEE Symposium on Security and Privacy (SP), 2027

   Bib

   @inproceedings{chen2027trust,
     author = {Chen, Zeyuan and Leng, Ye and Cui, Chi and Liang, Mengfei and Shao, Bo and Zhang, Xinyu and Shen, Yun and Backes, Michael and Shen, Xinyue and Zhang, Yang},
     title = {{Can We Trust LLM Security Research? A Reproducibility Study of Large Language Model Security Papers in Tier-1 Security Conference}},
     booktitle = {Proceedings of the 2027 IEEE Symposium on Security and Privacy (SP)},
     publisher = {IEEE},
     year = {2027},
   }

2026

1. EMNLP Findings

   Beyond Text-Intrinsic Features: An Agentic Framework for Evidence-Based AI-Generated Text Detection

   Chi Cui, Yixin Wu, Michael Backes, and Yang Zhang

   In The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026

   Bib PDF Code

   @inproceedings{CWZBEMNLP26,
     author = {Cui, Chi and Wu, Yixin and Backes, Michael and Zhang, Yang},
     title = {{Beyond Text-Intrinsic Features: An Agentic Framework for Evidence-Based AI-Generated Text Detection}},
     booktitle = {{The Conference on Empirical Methods in Natural Language Processing (EMNLP)}},
     publisher = {ACL},
     year = {2026},
   }

2. arXiv

   From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan

   Chi Cui, Yixin Wu, and Yang Zhang

   2026

   DOI Bib HTML PDF

   @misc{CuiWZ26,
     author = {Cui, Chi and Wu, Yixin and Zhang, Yang},
     title = {{From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan}},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.CY},
     doi = {10.48550/arXiv.2606.27234},
   }

3. ACL Findings

   Rethinking Assessments of Prompt Injection Attacks

   Chi Cui, Yixin Wu, Michael Backes, and Yang Zhang

   In Annual Meeting of the Association for Computational Linguistics (ACL), 2026

   Bib PDF Code

   @inproceedings{CWBZ26,
     author = {Cui, Chi and Wu, Yixin and Backes, Michael and Zhang, Yang},
     title = {{Rethinking Assessments of Prompt Injection Attacks}},
     booktitle = {{Annual Meeting of the Association for Computational Linguistics (ACL)}},
     publisher = {ACL},
     year = {2026},
   }

4. ACL Findings

   InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents

   Yixin Wu, Rui Wen, Chi Cui, Michael Backes, and Yang Zhang

   In Annual Meeting of the Association for Computational Linguistics (ACL), 2026

   Bib PDF Code

   @inproceedings{WWCBZ26,
     author = {Wu, Yixin and Wen, Rui and Cui, Chi and Backes, Michael and Zhang, Yang},
     title = {{InferPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents}},
     booktitle = {{Annual Meeting of the Association for Computational Linguistics (ACL)}},
     publisher = {ACL},
     year = {2026},
   }