Keyan Guo

Keyan Guo

I am a PhD candidate in the Department of Computer Science and Engineering at University at Buffalo, supervised by Dr. Hongxin Hu. My background is in AI and cybersecurity, and I am strongly interested in developing AI-driven solutions to address real-world security challenges and enhance AI safety and robustness.

Keyan Guo

AI Security Researcher

Building safer generative AI systems against real-world threats.

I am a 4th-year Ph.D. candidate in Computer Science and Engineering at the University at Buffalo, SUNY, advised by Dr. Hongxin Hu. My research sits at the intersection of generative AI security, adversarial robustness, and platform safety, with a focus on making large-scale AI systems more trustworthy in deployment.

View Publications Read CV Contact Me

I welcome research collaboration and I am actively looking for research internships in 2026.

Research Focus

  • Generative AI security and safety
  • Adversarial robustness for multimodal models
  • Online abuse, harmful meme, and hate content moderation
  • AI systems for real-world security and public-good applications

Selected Highlights

  • CHI 2026 paper on parent-child perspectives in children's online safety
  • EMNLP 2025 paper on hateful video detection with multimodal LLMs
  • USENIX Security 2025 paper on defending LLMs against jailbreak attacks
  • NDSS 2025 paper on harmful meme understanding and detection
  • NDSS 2025 Internet Society Fellow
  • USENIX Security 2024 paper on moderating unsafe user-generated content games
  • IEEE S&P 2024 paper on online hate moderation with chain-of-thought reasoning

Recent News

  • Service 03/2026: I am honored to serve on the IEEE Security and Privacy 2026 Artifact Evaluation Committee.
  • Paper 01/2026: Our work Beyond Age-Based Restrictions: Rethinking Children’s Online Safety Through Comparing Parent-Child Perspectives of Risks in User-Generated Content was accepted to CHI 2026.
  • Paper 09/2025: Our research on automatic hate video detection was accepted to EMNLP 2025.
  • Service 07/2025: I joined the NDSS 2026 Artifact Evaluation Committee.
  • Service 05/2025: I served on the ASONAM 2025 Program Committee.
  • Talk 02/2025: I presented I know what you MEME! Understanding and Detecting Harmful Memes with Multimodal Large Language Models at NDSS 2025.
  • Paper 02/2025: Our work on detecting and mitigating jailbreak attacks for large language models was accepted to USENIX Security 2025.
  • Award 01/2025: I was selected as an Internet Society Fellowship recipient for NDSS 2025.
  • Award 12/2024: I received the CSE Best Research Project (PhD) Award at the University at Buffalo.
  • Service 11/2024: I joined the artifact technical program committee for the 34th USENIX Security Symposium.
  • Paper 10/2024: Our work on harmful meme detection was accepted to NDSS 2025.
  • Paper 10/2024: Our work on AI-cybersecurity education with cyberharassment detection labs was accepted to CISSE 2024.
  • Paper 10/2024: Our work on an AI-centered social cybersecurity education platform was accepted to CISSE 2024.
  • Paper 10/2024: Our study on understanding cyberbullying images was accepted to ICMLA 2024.
  • Talk 08/2024: I presented Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models at the 33rd USENIX Security Symposium.
  • Award 07/2024: I received a USENIX Conference Student Grant.
  • Talk 06/2024: I presented the tutorial Machine Learning Based Online Abuse Defense: Platform, Research, and Hands-on Labs at ICWSM 2024.
  • Media 05/2024: Our work on unsafe user-generated content was selected as a poster at the 45th IEEE Symposium on Security and Privacy.
  • Paper 04/2024: We had an accepted position statement at a CHI 2024 Workshop.
  • Media 04/2024: Our ASONAM 2023 paper on COVID-19-related online hate propagation through hateful memes was selected for the ACM Showcase on Kudos.
  • Paper 03/2024: Our paper Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models was accepted to USENIX Security 2024.
  • Award 12/2023: I won the 2023 Annual CSE Poster Competition and received the CSE Best AI Poster Award at the University at Buffalo.
  • Talk 12/2023: I presented An Investigation of Large Language Models for Real-World Hate Speech Detection at ICMLA 2023.
  • Paper 10/2023: Our paper Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models was accepted to IEEE S&P 2024.
  • Paper 10/2023: Our paper An Investigation of Large Language Models for Real-World Hate Speech Detection was accepted to ICMLA 2023.
  • Talk 09/2023: I presented Understanding and Measuring Robustness of Vision and Language Multimodal Models at SKM 2023.
  • Paper 09/2023: Our paper on COVID-19-related online hate propagation through hateful memes was accepted to ASONAM 2023.
  • Paper 08/2023: Our paper AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab was accepted to FIE 2023.
  • Paper 08/2023: Our paper Understanding and Measuring Robustness of Vision and Language Multimodal Models was accepted to SKM 2023.
  • Paper 08/2023: Our paper Exploring Vulnerabilities in Voice Command Skills for Connected Vehicles was accepted to EAI SmartSP 2023.
  • Talk 04/2023: I presented Mitigating Online Hate in the Evolving Cyber Environment: Rapid Adaptation and Moderation of Emerging Threats at GLSD 2023.
  • Paper 11/2022: Our paper on the generalizability of hateful memes detection models against COVID-19-related hateful memes was accepted to ICMLA 2022.
  • Award 11/2022: I received the CSE Best Graduate Teaching Award at the University at Buffalo.
  • Talk 11/2022: We presented the demo paper Understanding the Effects of Paint Colors on LiDAR Point Cloud Intensities at AutoSec 2022.

Collaborators

Faculty Collaborators

Dr. Hongxin Hu, Dr. Ziming Zhao, Dr. Nishant Vishwamitra, Dr. Long Cheng, Dr. Guo Freeman, Dr. Qian Wang, Dr. Juan Wang, Dr. Yongkai Wu, Dr. Xiaohong Yuan, Dr. Chunming Qiao, Dr. Feng Luo, Dr. Jeannette Wade

Ph.D. Student Collaborators

Ebuka Okpala, Feng Wei, Foad Hajiaghajani, Gaoxiang Liu, Isabelle Ondracek, Song Liao, Md. Armanuzzaman Tomal, Mohammed Aldeen, Qiqing Huang, Rupam Patir, Wenbo Ding, Xi Tan, Yong Zhuang, Shenyi Zhang, Zheyuan Ma

Sorted alphabetically by first name.

Undergraduate and Graduate Student Collaborators

Amardhruva Narasimha Prabhu, Ayush Utkarsh, Pal Dave, Radhika Singh, Shaik Sabiha

Sorted alphabetically by first name.

High School Student Collaborators

Alexander Hu (now at UCLA), David Cong (now at Duke University), Helen Qin, Ishan Ajay, Jaden Mu (now at Carnegie Mellon University), Johnson Chen, Wentai Zhao (now at the University of Michigan)

Sorted alphabetically by first name.