Scholar
Hanxi Guo
Google Scholar ID: R3C7RsSZnjYC
Purdue University
Citations & Impact
Citations
138
H-index
5
i10-index
5
Publications
14
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- - Paper “Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis” accepted by EMNLP 2025
- - Team PurCL won the first place in the Amazon Nova AI Challenge and released system description “ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants”
- - Paper “JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models” accepted by ICCV 2025
- - Paper “SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks” accepted by USENIX Security 2025
- - Paper “MultiVerse: Exposing Large Language Model Alignment Problems in Diverse Worlds” accepted by NeurIPS 2024 Workshop on Safe GenAI
- - Paper “SkewAct: Red Teaming Large Language Models via Activation-Skewed Adversarial Prompt Optimization” accepted by NeurIPS 2024 Workshop on Red Teaming GenAI
- - Paper “BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens” accepted by NeurIPS 2024
- - Paper “BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target” accepted by S&P 2025
- - Preprint “Poisoning with A Pill: Circumventing Detection in Federated Learning” released
- - Paper “UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening” accepted by ECCV 2024
- - Paper “Siren+: Robust Federated Learning with Proactive Alarming and Differential Privacy” accepted by IEEE TDSC
- - Paper “Siren: Byzantine-robust Federated Learning via Proactive Alarming” accepted by SoCC 2021
- - Paper “SpaceDML: Enabling Distributed Machine Learning in Space Information Networks” accepted by IEEE Network
Research Experience
- - Ph.D. student in the Department of Computer Science at Purdue University, involved in multiple research projects
Education
- - Ph.D.: Computer Science, Purdue University, advised by Prof. Xiangyu Zhang
- - M.Eng. and B.Eng.: Computer Science, Shanghai Jiao Tong University (SJTU), supervised by Prof. Ruhui Ma and Prof. Tao Song
- - Worked with Prof. Yang Hua and Prof. Hao Wang
Background
- - Research Interests: AI Security and Ethics, especially for such topics in Federated Learning and Large Language Models
- - Currently a third-year Ph.D. student in Computer Science at Purdue University
Co-authors