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.

Publications

A complete list is also available on Google Scholar. * denotes equal contribution.

2027

  • NDSS 2027 AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan, Jiawei Liu, Zhiquan Liu, Hongxin Hu Network and Distributed System Security Symposium (NDSS), 2027.

2026

  • CCS 2026 MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration Shenyi Zhang, Keyan Guo, Zihao Wang, Xuebin Li, Lingchen Zhao, Hongxin Hu, Chao Shen, Qian Wang ACM Conference on Computer and Communications Security (CCS), 2026.
  • EMNLP 2026 DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents Rupam Patir*, Keyan Guo*, Suvadra Barua, Abhijeet Pathak, Dinesh Gudimetla, Jiawei Guo, Hongxin Hu, Haipeng Cai Findings of the Association for Computational Linguistics: EMNLP 2026.
  • CHI 2026 Beyond Age-Based Restrictions: Rethinking Children's Online Safety Through Comparing Parent–Child Perspectives of Risks in User-Generated Content Games Ruchi Panchanadikar, Yang Hu*, Keyan Guo*, Amelia L Hall, Hongxin Hu, Nishant Vishwamitra, Guo Freeman ACM CHI Conference on Human Factors in Computing Systems (CHI), 2026. [PDF]

2025

  • EMNLP 2025 HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025. [PDF]
  • USENIX Security 2025 JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation Shenyi Zhang, Yuchen Zhai, Keyan Guo, Hongxin Hu, Shengnan Guo, Zheng Fang, Lingchen Zhao, Chao Shen, Cong Wang, Qian Wang 34th USENIX Security Symposium (USENIX Security), 2025. [PDF]
  • NDSS 2025 I know what you MEME! Understanding and Detecting Harmful Memes with Multimodal Large Language Models Yong Zhuang*, Keyan Guo*, Juan Wang, Yiheng Jing, Xiaoyang Xu, Wenzhe Yi, Mengda Yang, Bo Zhao, Hongxin Hu Network and Distributed System Security Symposium (NDSS), 2025. [PDF]
  • ICMLA 2025 Toward Unified Moderation of Cyberbullying Across Social Media and Video Games David Cong, Keyan Guo, Hongxin Hu International Conference on Machine Learning and Applications (ICMLA), 2025.
  • JCISSE 2025 AI-Cybersecurity Education Through Designing AI-based Cyberharassment Detection Lab Ebuka Okpala, Nishant Vishwamitra, Keyan Guo, Song Liao, Long Cheng, Hongxin Hu, Xiaohong Yuan, Jeannette Wade, Sajad Khorsandroo Journal of the Colloquium for Information Systems Security Education (JCISSE), vol. 12, no. 1, 2025.
  • JCISSE 2025 Enhancing AI-Centered Social Cybersecurity Education through Learning Platform Design Nishant Vishwamitra, Ebuka Okpala, Song Liao, Keyan Guo, Sandeep Shah, Hongxin Hu, Xiaohong Yuan, Long Cheng Journal of the Colloquium for Information Systems Security Education (JCISSE), vol. 12, no. 1, 2025.
  • FutureG 2025 Towards LLM-Assisted Vulnerability Detection and Repair for Open-Source 5G UE Implementations Rupam Patir, Qiqing Huang, Keyan Guo, Wanda Guo, Guofei Gu, Haipeng Cai, Hongxin Hu Workshop on Security and Privacy of Next-Generation Networks (FutureG), co-located with NDSS 2025.

2024

  • USENIX Security 2024 Moderating Illicit Online Image Promotion for Unsafe User-Generated Content Games Using Large Vision-Language Models Keyan Guo, Ayush Utkarsh, Wenbo Ding, Isabelle Ondracek, Ziming Zhao, Guo Freeman, Nishant Vishwamitra, Hongxin Hu 33rd USENIX Security Symposium (USENIX Security), 2024. [PDF]
  • IEEE S&P 2024 Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models Nishant Vishwamitra*, Keyan Guo*, Farhan Tajwar Romit, Isabelle Ondracek, Long Cheng, Ziming Zhao, Hongxin Hu 45th IEEE Symposium on Security and Privacy (IEEE S&P), 2024. [PDF]
  • ICMLA 2024 Detecting Cyberbullying in Visual Content: A Large Vision-Language Model Approach Jaden Mu, David Cong, Helen Qin, Ishan Ajay, Keyan Guo, Nishant Vishwamitra, Hongxin Hu International Conference on Machine Learning and Applications (ICMLA), 2024.
  • CHI EA 2024 Moderating Embodied Cyber Threats Using Generative AI Keyan Guo, Guo Freeman, Hongxin Hu Position paper, CHI 2024 Workshop on Novel Approaches for Understanding and Mitigating Emerging New Harms in Immersive and Embodied Virtual Spaces.

2023

  • ICMLA 2023 An Investigation of Large Language Models for Real-World Hate Speech Detection Keyan Guo, Alexander Hu, Jaden Mu, Ziheng Shi, Ziming Zhao, Nishant Vishwamitra, Hongxin Hu 22nd IEEE International Conference on Machine Learning and Applications (ICMLA), 2023. [PDF]
  • ASONAM 2023 Understanding and Analyzing COVID-19-related Online Hate Propagation Through Hateful Memes Shared on Twitter Nishant Vishwamitra, Keyan Guo, Song Liao, Jaden Mu, Zheyuan Ma, Long Cheng, Ziming Zhao, Hongxin Hu IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2023.
  • SKM 2023 Understanding and Measuring Robustness of Vision and Language Multimodal Models Nishant Vishwamitra, Keyan Guo, Hongxin Hu, Ziming Zhao, Feng Luo International Conference on Secure Knowledge Management (SKM), 2023. [PDF]
  • SmartSP 2023 Exploring Vulnerabilities in Voice Command Skills for Connected Vehicles Wenbo Ding, Song Liao, Keyan Guo, Fuqiang Zhang, Long Cheng, Ziming Zhao, Hongxin Hu EAI International Conference on Security and Privacy in Cyber-Physical Systems and Smart Vehicles (EAI SmartSP), 2023.

2022

  • ICMLA 2022 Understanding the Generalizability of Hateful Memes Detection Models Against COVID-19-related Hateful Memes Keyan Guo, Wentai Zhao, Jaden Mu, Nishant Vishwamitra, Ziming Zhao, Hongxin Hu 21st IEEE International Conference on Machine Learning and Applications (ICMLA), 2022.
  • AutoSec 2022 Understanding the Effects of Paint Colors on LiDAR Perceptions Shaik Sabiha, Keyan Guo, Foad Hajiaghajani, Chunming Qiao, Hongxin Hu, Ziming Zhao Workshop on Automotive and Autonomous Vehicle Security (AutoSec), 2022.