Hanxi Guo

Computer Science · Purdue University West Lafayette

Early career · publishing since 2021Rising activity

Adversarial Robustness in Machine Learning Privacy-Preserving Technologies in Data Topic Modeling Cryptography and Data Security Anomaly Detection Techniques and Applications

Publications

Citations

Est. group size

—

Recurring co-author estimate

Active years

Publishing since 2021

Research summary

AI-generated

Hanxi Guo's research focuses on security and privacy issues in machine learning systems, including how AI models like federated learning setups and large language models (LLMs) can be attacked (e.g., data poisoning, jailbreaking, backdoors) and defended (e.g., detection methods, privacy-preserving fine-tuning). The work spans practical benchmarks for detecting AI-generated content and robustness testing for both traditional machine learning and generative AI systems such as diffusion models.

Security and robustness of federated learningAttacks and defenses for large language models (LLMs)Privacy-preserving machine learningDetection of AI-generated contentRobustness testing of generative AI models (e.g., diffusion models)

Publication output was minimal or absent from 2017-2020, then increased sharply starting in 2021 and grew substantially through 2024-2026, indicating a recent and active research period.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence

Publications per year over the last 10 years — averaging 3.0/year recently

Recent publications

Poisoning with a Pill: Circumventing Detection in Federated Learning
Open MIND · 2026
Poisoning with a Pill: Circumventing Detection in Federated Learning
Proceedings of the AAAI Conference on Artificial Intelligence · 2026
CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs
arXiv (Cornell University) · 2025
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
arXiv (Cornell University) · 2025
SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks
arXiv (Cornell University) · 2025
An Automated Framework for Beef-Quality Assessment Using an e-nose and TPE-FL-XGBoost
2025
JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models
2025
Siren+: Robust Federated Learning With Proactive Alarming and Differential Privacy
IEEE Transactions on Dependable and Secure Computing · 2024
Poisoning with A Pill: Circumventing Detection in Federated Learning
arXiv (Cornell University) · 2024
SpaceDML: Enabling Distributed Machine Learning in Space Information Networks
IEEE Network · 2021
Siren
2021

Publishes in

arXiv (Cornell University)×5
IEEE Transactions on Dependable and Secure Computing×1
IEEE Network×1
Lecture notes in computer science×1
Open MIND×1

Similar researchers

By research-topic overlap

Siyuan Cheng
Computer Science · Purdue University West Lafayette
Xinyue Shen
Computer Science · Indiana University
Xiaoyi Chen
Computer Science · Indiana University
Shengwei An
Computer Science · Purdue University West Lafayette
Guangyu Shen
Computer Science · Purdue University West Lafayette

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile